Initial commit of project with LFS

.gitattributes

@@ -0,0 +1,5 @@
+*.json filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.so filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,437 @@
+Attribution-NonCommercial-ShareAlike 4.0 International
+
+=======================================================================
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of
+Creative Commons public licenses does not create a lawyer-client or
+other relationship. Creative Commons makes its licenses and related
+information available on an "as-is" basis. Creative Commons gives no
+warranties regarding its licenses, any material licensed under their
+terms and conditions, or any related information. Creative Commons
+disclaims all liability for damages resulting from their use to the
+fullest extent possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share
+original works of authorship and other material subject to copyright
+and certain other rights specified in the public license below. The
+following considerations are for informational purposes only, are not
+exhaustive, and do not form part of our licenses.
+
+     Considerations for licensors: Our public licenses are
+     intended for use by those authorized to give the public
+     permission to use material in ways otherwise restricted by
+     copyright and certain other rights. Our licenses are
+     irrevocable. Licensors should read and understand the terms
+     and conditions of the license they choose before applying it.
+     Licensors should also secure all rights necessary before
+     applying our licenses so that the public can reuse the
+     material as expected. Licensors should clearly mark any
+     material not subject to the license. This includes other CC-
+     licensed material, or material used under an exception or
+     limitation to copyright. More considerations for licensors:
+    wiki.creativecommons.org/Considerations_for_licensors
+
+     Considerations for the public: By using one of our public
+     licenses, a licensor grants the public permission to use the
+     licensed material under specified terms and conditions. If
+     the licensor's permission is not necessary for any reason--for
+     example, because of any applicable exception or limitation to
+     copyright--then that use is not regulated by the license. Our
+     licenses grant only permissions under copyright and certain
+     other rights that a licensor has authority to grant. Use of
+     the licensed material may still be restricted for other
+     reasons, including because others have copyright or other
+     rights in the material. A licensor may make special requests,
+     such as asking that all changes be marked or described.
+     Although not required by our licenses, you are encouraged to
+     respect those requests where reasonable. More considerations
+     for the public:
+    wiki.creativecommons.org/Considerations_for_licensees
+
+=======================================================================
+
+Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
+Public License
+
+By exercising the Licensed Rights (defined below), You accept and agree
+to be bound by the terms and conditions of this Creative Commons
+Attribution-NonCommercial-ShareAlike 4.0 International Public License
+("Public License"). To the extent this Public License may be
+interpreted as a contract, You are granted the Licensed Rights in
+consideration of Your acceptance of these terms and conditions, and the
+Licensor grants You such rights in consideration of benefits the
+Licensor receives from making the Licensed Material available under
+these terms and conditions.
+
+
+Section 1 -- Definitions.
+
+  a. Adapted Material means material subject to Copyright and Similar
+     Rights that is derived from or based upon the Licensed Material
+     and in which the Licensed Material is translated, altered,
+     arranged, transformed, or otherwise modified in a manner requiring
+     permission under the Copyright and Similar Rights held by the
+     Licensor. For purposes of this Public License, where the Licensed
+     Material is a musical work, performance, or sound recording,
+     Adapted Material is always produced where the Licensed Material is
+     synched in timed relation with a moving image.
+
+  b. Adapter's License means the license You apply to Your Copyright
+     and Similar Rights in Your contributions to Adapted Material in
+     accordance with the terms and conditions of this Public License.
+
+  c. BY-NC-SA Compatible License means a license listed at
+     creativecommons.org/compatiblelicenses, approved by Creative
+     Commons as essentially the equivalent of this Public License.
+
+  d. Copyright and Similar Rights means copyright and/or similar rights
+     closely related to copyright including, without limitation,
+     performance, broadcast, sound recording, and Sui Generis Database
+     Rights, without regard to how the rights are labeled or
+     categorized. For purposes of this Public License, the rights
+     specified in Section 2(b)(1)-(2) are not Copyright and Similar
+     Rights.
+
+  e. Effective Technological Measures means those measures that, in the
+     absence of proper authority, may not be circumvented under laws
+     fulfilling obligations under Article 11 of the WIPO Copyright
+     Treaty adopted on December 20, 1996, and/or similar international
+     agreements.
+
+  f. Exceptions and Limitations means fair use, fair dealing, and/or
+     any other exception or limitation to Copyright and Similar Rights
+     that applies to Your use of the Licensed Material.
+
+  g. License Elements means the license attributes listed in the name
+     of a Creative Commons Public License. The License Elements of this
+     Public License are Attribution, NonCommercial, and ShareAlike.
+
+  h. Licensed Material means the artistic or literary work, database,
+     or other material to which the Licensor applied this Public
+     License.
+
+  i. Licensed Rights means the rights granted to You subject to the
+     terms and conditions of this Public License, which are limited to
+     all Copyright and Similar Rights that apply to Your use of the
+     Licensed Material and that the Licensor has authority to license.
+
+  j. Licensor means the individual(s) or entity(ies) granting rights
+     under this Public License.
+
+  k. NonCommercial means not primarily intended for or directed towards
+     commercial advantage or monetary compensation. For purposes of
+     this Public License, the exchange of the Licensed Material for
+     other material subject to Copyright and Similar Rights by digital
+     file-sharing or similar means is NonCommercial provided there is
+     no payment of monetary compensation in connection with the
+     exchange.
+
+  l. Share means to provide material to the public by any means or
+     process that requires permission under the Licensed Rights, such
+     as reproduction, public display, public performance, distribution,
+     dissemination, communication, or importation, and to make material
+     available to the public including in ways that members of the
+     public may access the material from a place and at a time
+     individually chosen by them.
+
+  m. Sui Generis Database Rights means rights other than copyright
+     resulting from Directive 96/9/EC of the European Parliament and of
+     the Council of 11 March 1996 on the legal protection of databases,
+     as amended and/or succeeded, as well as other essentially
+     equivalent rights anywhere in the world.
+
+  n. You means the individual or entity exercising the Licensed Rights
+     under this Public License. Your has a corresponding meaning.
+
+
+Section 2 -- Scope.
+
+  a. License grant.
+
+       1. Subject to the terms and conditions of this Public License,
+          the Licensor hereby grants You a worldwide, royalty-free,
+          non-sublicensable, non-exclusive, irrevocable license to
+          exercise the Licensed Rights in the Licensed Material to:
+
+            a. reproduce and Share the Licensed Material, in whole or
+               in part, for NonCommercial purposes only; and
+
+            b. produce, reproduce, and Share Adapted Material for
+               NonCommercial purposes only.
+
+       2. Exceptions and Limitations. For the avoidance of doubt, where
+          Exceptions and Limitations apply to Your use, this Public
+          License does not apply, and You do not need to comply with
+          its terms and conditions.
+
+       3. Term. The term of this Public License is specified in Section
+          6(a).
+
+       4. Media and formats; technical modifications allowed. The
+          Licensor authorizes You to exercise the Licensed Rights in
+          all media and formats whether now known or hereafter created,
+          and to make technical modifications necessary to do so. The
+          Licensor waives and/or agrees not to assert any right or
+          authority to forbid You from making technical modifications
+          necessary to exercise the Licensed Rights, including
+          technical modifications necessary to circumvent Effective
+          Technological Measures. For purposes of this Public License,
+          simply making modifications authorized by this Section 2(a)
+          (4) never produces Adapted Material.
+
+       5. Downstream recipients.
+
+            a. Offer from the Licensor -- Licensed Material. Every
+               recipient of the Licensed Material automatically
+               receives an offer from the Licensor to exercise the
+               Licensed Rights under the terms and conditions of this
+               Public License.
+
+            b. Additional offer from the Licensor -- Adapted Material.
+               Every recipient of Adapted Material from You
+               automatically receives an offer from the Licensor to
+               exercise the Licensed Rights in the Adapted Material
+               under the conditions of the Adapter's License You apply.
+
+            c. No downstream restrictions. You may not offer or impose
+               any additional or different terms or conditions on, or
+               apply any Effective Technological Measures to, the
+               Licensed Material if doing so restricts exercise of the
+               Licensed Rights by any recipient of the Licensed
+               Material.
+
+       6. No endorsement. Nothing in this Public License constitutes or
+          may be construed as permission to assert or imply that You
+          are, or that Your use of the Licensed Material is, connected
+          with, or sponsored, endorsed, or granted official status by,
+          the Licensor or others designated to receive attribution as
+          provided in Section 3(a)(1)(A)(i).
+
+  b. Other rights.
+
+       1. Moral rights, such as the right of integrity, are not
+          licensed under this Public License, nor are publicity,
+          privacy, and/or other similar personality rights; however, to
+          the extent possible, the Licensor waives and/or agrees not to
+          assert any such rights held by the Licensor to the limited
+          extent necessary to allow You to exercise the Licensed
+          Rights, but not otherwise.
+
+       2. Patent and trademark rights are not licensed under this
+          Public License.
+
+       3. To the extent possible, the Licensor waives any right to
+          collect royalties from You for the exercise of the Licensed
+          Rights, whether directly or through a collecting society
+          under any voluntary or waivable statutory or compulsory
+          licensing scheme. In all other cases the Licensor expressly
+          reserves any right to collect such royalties, including when
+          the Licensed Material is used other than for NonCommercial
+          purposes.
+
+
+Section 3 -- License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+  a. Attribution.
+
+       1. If You Share the Licensed Material (including in modified
+          form), You must:
+
+            a. retain the following if it is supplied by the Licensor
+               with the Licensed Material:
+
+                 i. identification of the creator(s) of the Licensed
+                    Material and any others designated to receive
+                    attribution, in any reasonable manner requested by
+                    the Licensor (including by pseudonym if
+                    designated);
+
+                ii. a copyright notice;
+
+               iii. a notice that refers to this Public License;
+
+                iv. a notice that refers to the disclaimer of
+                    warranties;
+
+                 v. a URI or hyperlink to the Licensed Material to the
+                    extent reasonably practicable;
+
+            b. indicate if You modified the Licensed Material and
+               retain an indication of any previous modifications; and
+
+            c. indicate the Licensed Material is licensed under this
+               Public License, and include the text of, or the URI or
+               hyperlink to, this Public License.
+
+       2. You may satisfy the conditions in Section 3(a)(1) in any
+          reasonable manner based on the medium, means, and context in
+          which You Share the Licensed Material. For example, it may be
+          reasonable to satisfy the conditions by providing a URI or
+          hyperlink to a resource that includes the required
+          information.
+       3. If requested by the Licensor, You must remove any of the
+          information required by Section 3(a)(1)(A) to the extent
+          reasonably practicable.
+
+  b. ShareAlike.
+
+     In addition to the conditions in Section 3(a), if You Share
+     Adapted Material You produce, the following conditions also apply.
+
+       1. The Adapter's License You apply must be a Creative Commons
+          license with the same License Elements, this version or
+          later, or a BY-NC-SA Compatible License.
+
+       2. You must include the text of, or the URI or hyperlink to, the
+          Adapter's License You apply. You may satisfy this condition
+          in any reasonable manner based on the medium, means, and
+          context in which You Share Adapted Material.
+
+       3. You may not offer or impose any additional or different terms
+          or conditions on, or apply any Effective Technological
+          Measures to, Adapted Material that restrict exercise of the
+          rights granted under the Adapter's License You apply.
+
+
+Section 4 -- Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that
+apply to Your use of the Licensed Material:
+
+  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
+     to extract, reuse, reproduce, and Share all or a substantial
+     portion of the contents of the database for NonCommercial purposes
+     only;
+
+  b. if You include all or a substantial portion of the database
+     contents in a database in which You have Sui Generis Database
+     Rights, then the database in which You have Sui Generis Database
+     Rights (but not its individual contents) is Adapted Material,
+     including for purposes of Section 3(b); and
+
+  c. You must comply with the conditions in Section 3(a) if You Share
+     all or a substantial portion of the contents of the database.
+
+For the avoidance of doubt, this Section 4 supplements and does not
+replace Your obligations under this Public License where the Licensed
+Rights include other Copyright and Similar Rights.
+
+
+Section 5 -- Disclaimer of Warranties and Limitation of Liability.
+
+  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
+     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
+     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
+     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
+     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
+     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
+     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
+     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
+     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
+     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
+
+  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
+     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
+     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
+     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
+     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
+     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
+     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
+     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
+     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
+
+  c. The disclaimer of warranties and limitation of liability provided
+     above shall be interpreted in a manner that, to the extent
+     possible, most closely approximates an absolute disclaimer and
+     waiver of all liability.
+
+
+Section 6 -- Term and Termination.
+
+  a. This Public License applies for the term of the Copyright and
+     Similar Rights licensed here. However, if You fail to comply with
+     this Public License, then Your rights under this Public License
+     terminate automatically.
+
+  b. Where Your right to use the Licensed Material has terminated under
+     Section 6(a), it reinstates:
+
+       1. automatically as of the date the violation is cured, provided
+          it is cured within 30 days of Your discovery of the
+          violation; or
+
+       2. upon express reinstatement by the Licensor.
+
+     For the avoidance of doubt, this Section 6(b) does not affect any
+     right the Licensor may have to seek remedies for Your violations
+     of this Public License.
+
+  c. For the avoidance of doubt, the Licensor may also offer the
+     Licensed Material under separate terms or conditions or stop
+     distributing the Licensed Material at any time; however, doing so
+     will not terminate this Public License.
+
+  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
+     License.
+
+
+Section 7 -- Other Terms and Conditions.
+
+  a. The Licensor shall not be bound by any additional or different
+     terms or conditions communicated by You unless expressly agreed.
+
+  b. Any arrangements, understandings, or agreements regarding the
+     Licensed Material not stated herein are separate from and
+     independent of the terms and conditions of this Public License.
+
+
+Section 8 -- Interpretation.
+
+  a. For the avoidance of doubt, this Public License does not, and
+     shall not be interpreted to, reduce, limit, restrict, or impose
+     conditions on any use of the Licensed Material that could lawfully
+     be made without permission under this Public License.
+
+  b. To the extent possible, if any provision of this Public License is
+     deemed unenforceable, it shall be automatically reformed to the
+     minimum extent necessary to make it enforceable. If the provision
+     cannot be reformed, it shall be severed from this Public License
+     without affecting the enforceability of the remaining terms and
+     conditions.
+
+  c. No term or condition of this Public License will be waived and no
+     failure to comply consented to unless expressly agreed to by the
+     Licensor.
+
+  d. Nothing in this Public License constitutes or may be interpreted
+     as a limitation upon, or waiver of, any privileges and immunities
+     that apply to the Licensor or You, including from the legal
+     processes of any jurisdiction or authority.
+
+=======================================================================
+
+Creative Commons is not a party to its public
+licenses. Notwithstanding, Creative Commons may elect to apply one of
+its public licenses to material it publishes and in those instances
+will be considered the “Licensor.” The text of the Creative Commons
+public licenses is dedicated to the public domain under the CC0 Public
+Domain Dedication. Except for the limited purpose of indicating that
+material is shared under a Creative Commons public license or as
+otherwise permitted by the Creative Commons policies published at
+creativecommons.org/policies, Creative Commons does not authorize the
+use of the trademark "Creative Commons" or any other trademark or logo
+of Creative Commons without its prior written consent including,
+without limitation, in connection with any unauthorized modifications
+to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For
+the avoidance of doubt, this paragraph does not form part of the
+public licenses.
+
+Creative Commons may be contacted at creativecommons.org.

README.md

@@ -0,0 +1,233 @@
+
+<div align="center">
+<h1>IDM-VTON: Improving Diffusion Models for Authentic Virtual Try-on in the Wild</h1>
+
+<a href='https://idm-vton.github.io'><img src='https://img.shields.io/badge/Project-Page-green'></a>
+<a href='https://arxiv.org/abs/2403.05139'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
+<a href='https://huggingface.co/spaces/yisol/IDM-VTON'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Demo-yellow'></a>
+<a href='https://huggingface.co/yisol/IDM-VTON'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-blue'></a>
+
+
+</div>
+
+This is the official implementation of the paper ["Improving Diffusion Models for Authentic Virtual Try-on in the Wild"](https://arxiv.org/abs/2403.05139).
+
+Star ⭐ us if you like it!
+
+---
+
+
+![teaser2](assets/teaser2.png)&nbsp;
+![teaser](assets/teaser.png)&nbsp;
+
+
+
+## Requirements
+
+```
+git clone https://github.com/yisol/IDM-VTON.git
+cd IDM-VTON
+
+conda env create -f environment.yaml
+conda activate idm
+```
+
+## Data preparation
+
+### VITON-HD
+You can download VITON-HD dataset from [VITON-HD](https://github.com/shadow2496/VITON-HD).
+
+After download VITON-HD dataset, move vitonhd_test_tagged.json into the test folder, and move vitonhd_train_tagged.json into the train folder.
+
+Structure of the Dataset directory should be as follows.
+
+```
+
+train
+|-- image
+|-- image-densepose
+|-- agnostic-mask
+|-- cloth
+|-- vitonhd_train_tagged.json
+
+test
+|-- image
+|-- image-densepose
+|-- agnostic-mask
+|-- cloth
+|-- vitonhd_test_tagged.json
+
+```
+
+### DressCode
+You can download DressCode dataset from [DressCode](https://github.com/aimagelab/dress-code).
+
+We provide pre-computed densepose images and captions for garments [here](https://kaistackr-my.sharepoint.com/:u:/g/personal/cpis7_kaist_ac_kr/EaIPRG-aiRRIopz9i002FOwBDa-0-BHUKVZ7Ia5yAVVG3A?e=YxkAip).
+
+We used [detectron2](https://github.com/facebookresearch/detectron2) for obtaining densepose images, refer [here](https://github.com/sangyun884/HR-VITON/issues/45) for more details.
+
+After download the DressCode dataset, place image-densepose directories and caption text files as follows.
+
+```
+DressCode
+|-- dresses
+    |-- images
+    |-- image-densepose
+    |-- dc_caption.txt
+    |-- ...
+|-- lower_body
+    |-- images
+    |-- image-densepose
+    |-- dc_caption.txt
+    |-- ...
+|-- upper_body
+    |-- images
+    |-- image-densepose
+    |-- dc_caption.txt
+    |-- ...
+```
+
+
+## Training
+
+
+### Preparation
+
+Download pre-trained ip-adapter for sdxl(IP-Adapter/sdxl_models/ip-adapter-plus_sdxl_vit-h.bin) and image encoder(IP-Adapter/models/image_encoder) [here](https://github.com/tencent-ailab/IP-Adapter).
+
+```
+git clone https://huggingface.co/h94/IP-Adapter
+```
+
+Move ip-adapter to ckpt/ip_adapter, and image encoder to ckpt/image_encoder.
+
+Start training using python file with arguments,
+
+```
+accelerate launch train_xl.py \
+    --gradient_checkpointing --use_8bit_adam \
+    --output_dir=result --train_batch_size=6 \
+    --data_dir=DATA_DIR
+```
+
+or, you can simply run with the script file.
+
+```
+sh train_xl.sh
+```
+
+
+## Inference
+
+
+### VITON-HD
+
+Inference using python file with arguments,
+
+```
+accelerate launch inference.py \
+    --width 768 --height 1024 --num_inference_steps 30 \
+    --output_dir "result" \
+    --unpaired \
+    --data_dir "DATA_DIR" \
+    --seed 42 \
+    --test_batch_size 2 \
+    --guidance_scale 2.0
+```
+
+or, you can simply run with the script file.
+
+```
+sh inference.sh
+```
+
+### DressCode
+
+For DressCode dataset, put the category you want to generate images via category argument,
+```
+accelerate launch inference_dc.py \
+    --width 768 --height 1024 --num_inference_steps 30 \
+    --output_dir "result" \
+    --unpaired \
+    --data_dir "DATA_DIR" \
+    --seed 42 
+    --test_batch_size 2
+    --guidance_scale 2.0
+    --category "upper_body" 
+```
+
+or, you can simply run with the script file.
+```
+sh inference.sh
+```
+
+## Start a local gradio demo <a href='https://github.com/gradio-app/gradio'><img src='https://img.shields.io/github/stars/gradio-app/gradio'></a>
+
+Download checkpoints for human parsing [here](https://huggingface.co/spaces/yisol/IDM-VTON/tree/main/ckpt).
+
+Place the checkpoints under the ckpt folder.
+```
+ckpt
+|-- densepose
+    |-- model_final_162be9.pkl
+|-- humanparsing
+    |-- parsing_atr.onnx
+    |-- parsing_lip.onnx
+
+|-- openpose
+    |-- ckpts
+        |-- body_pose_model.pth
+    
+```
+
+
+
+
+Run the following command:
+
+```python
+python gradio_demo/app.py
+```
+
+
+
+
+
+
+## Acknowledgements
+
+
+Thanks [ZeroGPU](https://huggingface.co/zero-gpu-explorers) for providing free GPU.
+
+Thanks [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter) for base codes.
+
+Thanks [OOTDiffusion](https://github.com/levihsu/OOTDiffusion) and [DCI-VTON](https://github.com/bcmi/DCI-VTON-Virtual-Try-On) for masking generation.
+
+Thanks [SCHP](https://github.com/GoGoDuck912/Self-Correction-Human-Parsing) for human segmentation.
+
+Thanks [Densepose](https://github.com/facebookresearch/DensePose) for human densepose.
+
+
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=yisol/IDM-VTON&type=Date)](https://star-history.com/#yisol/IDM-VTON&Date)
+
+
+
+## Citation
+```
+@article{choi2024improving,
+  title={Improving Diffusion Models for Authentic Virtual Try-on in the Wild},
+  author={Choi, Yisol and Kwak, Sangkyung and Lee, Kyungmin and Choi, Hyungwon and Shin, Jinwoo},
+  journal={arXiv preprint arXiv:2403.05139},
+  year={2024}
+}
+```
+
+
+
+## License
+The codes and checkpoints in this repository are under the [CC BY-NC-SA 4.0 license](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
+
+

ckpt/densepose/model_final_162be9.pkl

@@ -0,0 +1 @@
+put model_final_162be9.pkl here

ckpt/humanparsing/parsing_atr.onnx

@@ -0,0 +1 @@
+put parsing_atr.onnx here

ckpt/humanparsing/parsing_lip.onnx

@@ -0,0 +1 @@
+put parsing_lip.onnx here

ckpt/image_encoder/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625d37b31afbf2f0792a87846b3654ee23f20568409e35b78a1f795b04e1a7a1
+size 560

ckpt/image_encoder/model.safetensors

@@ -0,0 +1 @@
+put image encoder ckpt here

ckpt/ip_adapter/ip-adapter-plus_sdxl_vit-h.bin

@@ -0,0 +1 @@
+put ip adapter ckpt here

ckpt/openpose/ckpts/body_pose_model.pth

@@ -0,0 +1 @@
+put body_pose_model.pth here

configs/Base-DensePose-RCNN-FPN.yaml

@@ -0,0 +1,48 @@
+VERSION: 2
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  BACKBONE:
+    NAME: "build_resnet_fpn_backbone"
+  RESNETS:
+    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
+  FPN:
+    IN_FEATURES: ["res2", "res3", "res4", "res5"]
+  ANCHOR_GENERATOR:
+    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
+    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
+  RPN:
+    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
+    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
+    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
+    # Detectron1 uses 2000 proposals per-batch,
+    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
+    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
+    POST_NMS_TOPK_TRAIN: 1000
+    POST_NMS_TOPK_TEST: 1000
+
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 2
+    POOLER_TYPE: "ROIAlign"
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+DATASETS:
+  TRAIN: ("densepose_coco_2014_train", "densepose_coco_2014_valminusminival")
+  TEST: ("densepose_coco_2014_minival",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.01
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+  WARMUP_FACTOR: 0.1
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)

configs/HRNet/densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dYBMemi9xOUFR0w"
+  BACKBONE:
+    NAME: "build_hrfpn_backbone"
+  RPN:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  ROI_HEADS:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: "norm"
+  BASE_LR: 0.03

configs/HRNet/densepose_rcnn_HRFPN_HRNet_w40_s1x.yaml

@@ -0,0 +1,23 @@
+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33ck0gvo5jfoWBOPo"
+  BACKBONE:
+    NAME: "build_hrfpn_backbone"
+  RPN:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  ROI_HEADS:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  HRNET:
+    STAGE2:
+      NUM_CHANNELS: [40, 80]
+    STAGE3:
+      NUM_CHANNELS: [40, 80, 160]
+    STAGE4:
+      NUM_CHANNELS: [40, 80, 160, 320]
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: "norm"
+  BASE_LR: 0.03

configs/HRNet/densepose_rcnn_HRFPN_HRNet_w48_s1x.yaml

@@ -0,0 +1,23 @@
+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dKvqI6pBZlifgJk"
+  BACKBONE:
+    NAME: "build_hrfpn_backbone"
+  RPN:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  ROI_HEADS:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  HRNET:
+    STAGE2:
+      NUM_CHANNELS: [48, 96]
+    STAGE3:
+      NUM_CHANNELS: [48, 96, 192]
+    STAGE4:
+      NUM_CHANNELS: [48, 96, 192, 384]
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: "norm"
+  BASE_LR: 0.03

configs/cse/Base-DensePose-RCNN-FPN-Human.yaml

@@ -0,0 +1,20 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  ROI_DENSEPOSE_HEAD:
+    CSE:
+      EMBEDDERS:
+        "smpl_27554":
+          TYPE: vertex_feature
+          NUM_VERTICES: 27554
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_smpl_27554_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_coco_2014_train_cse"
+    - "densepose_coco_2014_valminusminival_cse"
+  TEST:
+    - "densepose_coco_2014_minival_cse"
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "smpl_27554"

configs/cse/Base-DensePose-RCNN-FPN.yaml

@@ -0,0 +1,60 @@
+VERSION: 2
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  BACKBONE:
+    NAME: "build_resnet_fpn_backbone"
+  RESNETS:
+    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
+  FPN:
+    IN_FEATURES: ["res2", "res3", "res4", "res5"]
+  ANCHOR_GENERATOR:
+    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
+    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
+  RPN:
+    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
+    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
+    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
+    # Detectron1 uses 2000 proposals per-batch,
+    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
+    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
+    POST_NMS_TOPK_TRAIN: 1000
+    POST_NMS_TOPK_TEST: 1000
+
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 2
+    POOLER_TYPE: "ROIAlign"
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    PREDICTOR_NAME: "DensePoseEmbeddingPredictor"
+    LOSS_NAME: "DensePoseCseLoss"
+    CSE:
+      # embedding loss, possible values:
+      # - "EmbeddingLoss"
+      # - "SoftEmbeddingLoss"
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.01
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+  WARMUP_FACTOR: 0.1
+  CLIP_GRADIENTS:
+    CLIP_TYPE: norm
+    CLIP_VALUE: 1.0
+    ENABLED: true
+    NORM_TYPE: 2.0
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+DENSEPOSE_EVALUATION:
+  TYPE: cse
+  STORAGE: file

configs/cse/densepose_rcnn_R_101_FPN_DL_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_101_FPN_DL_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_101_FPN_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_101_FPN_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_DL_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_DL_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_16k.yaml

@@ -0,0 +1,133 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CATEGORY_MAPS:
+    "densepose_lvis_v1_ds2_train_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+    "densepose_lvis_v1_ds2_val_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+  CLASS_TO_MESH_NAME_MAPPING:
+    # Note: different classes are mapped to a single class
+    # mesh is chosen based on GT data, so this is just some
+    # value which has no particular meaning
+    "0": "sheep_5004"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_4k.yaml

@@ -0,0 +1,133 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_5001":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5001
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_5001_256.pkl"
+        "dog_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_5002_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds1_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds1_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds1_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds1_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CATEGORY_MAPS:
+    "densepose_lvis_v1_ds1_train_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+    "densepose_lvis_v1_ds1_val_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+  CLASS_TO_MESH_NAME_MAPPING:
+    # Note: different classes are mapped to a single class
+    # mesh is chosen based on GT data, so this is just some
+    # value which has no particular meaning
+    "0": "sheep_5004"
+SOLVER:
+  MAX_ITER: 4000
+  STEPS: (3000, 3500)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_16k.yaml

@@ -0,0 +1,119 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/270668502/model_final_21b1d2.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_i2m_16k.yaml

@@ -0,0 +1,121 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/270668502/model_final_21b1d2.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      PIX_TO_SHAPE_CYCLE_LOSS:
+        ENABLED: True
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_m2m_16k.yaml

@@ -0,0 +1,138 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/267687159/model_final_354e61.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      SHAPE_TO_SHAPE_CYCLE_LOSS:
+        ENABLED: True
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+        "smpl_27554":
+          TYPE: vertex_feature
+          NUM_VERTICES: 27554
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_smpl_27554_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True
+  MESH_ALIGNMENT_MESH_NAMES:
+    - bear_4936
+    - cow_5002
+    - cat_7466
+    - dog_7466
+    - elephant_5002
+    - giraffe_5002
+    - horse_5004
+    - sheep_5004
+    - zebra_5002

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_16k.yaml

@@ -0,0 +1,119 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_4k.yaml

@@ -0,0 +1,119 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_5001":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5001
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_5001_256.pkl"
+        "dog_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_5002_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds1_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds1_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds1_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds1_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_5001"
+    "3": "dog_5002"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 4000
+  STEPS: (3000, 3500)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k.yaml

@@ -0,0 +1,118 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBED_LOSS_WEIGHT: 0.0
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 24000
+  STEPS: (20000, 22000)

configs/cse/densepose_rcnn_R_50_FPN_soft_chimps_finetune_4k.yaml

@@ -0,0 +1,29 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "chimp_5029":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5029
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_chimp_5029_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_chimps_cse_train"
+  TEST:
+    - "densepose_chimps_cse_val"
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "chimp_5029"
+SOLVER:
+  MAX_ITER: 4000
+  STEPS: (3000, 3500)

configs/cse/densepose_rcnn_R_50_FPN_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC1M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC1_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC2M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC2_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_s1x.yaml

@@ -0,0 +1,10 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_WC1M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_WC1_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_WC2M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_WC2_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_s1x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_s1x_legacy.yaml

@@ -0,0 +1,17 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NUM_COARSE_SEGM_CHANNELS: 15
+    POOLER_RESOLUTION: 14
+    HEATMAP_SIZE: 56
+    INDEX_WEIGHTS: 2.0
+    PART_WEIGHTS: 0.3
+    POINT_REGRESSION_WEIGHTS: 0.1
+    DECODER_ON: False
+SOLVER:
+  BASE_LR: 0.002
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_WC1M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_WC1_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_WC2M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)