Papers
arxiv:2510.07723

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

Published on Oct 9
· Submitted by Adina Yakefu on Oct 28
Authors:
,
,
,
,
,
,
,

Abstract

SyncHuman combines 2D multiview and 3D native generative models with pixel-aligned synchronization and feature injection to achieve high-quality, photorealistic 3D human reconstruction from single images.

AI-generated summary

Photorealistic 3D full-body human reconstruction from a single image is a critical yet challenging task for applications in films and video games due to inherent ambiguities and severe self-occlusions. While recent approaches leverage SMPL estimation and SMPL-conditioned image generative models to hallucinate novel views, they suffer from inaccurate 3D priors estimated from SMPL meshes and have difficulty in handling difficult human poses and reconstructing fine details. In this paper, we propose SyncHuman, a novel framework that combines 2D multiview generative model and 3D native generative model for the first time, enabling high-quality clothed human mesh reconstruction from single-view images even under challenging human poses. Multiview generative model excels at capturing fine 2D details but struggles with structural consistency, whereas 3D native generative model generates coarse yet structurally consistent 3D shapes. By integrating the complementary strengths of these two approaches, we develop a more effective generation framework. Specifically, we first jointly fine-tune the multiview generative model and the 3D native generative model with proposed pixel-aligned 2D-3D synchronization attention to produce geometrically aligned 3D shapes and 2D multiview images. To further improve details, we introduce a feature injection mechanism that lifts fine details from 2D multiview images onto the aligned 3D shapes, enabling accurate and high-fidelity reconstruction. Extensive experiments demonstrate that SyncHuman achieves robust and photo-realistic 3D human reconstruction, even for images with challenging poses. Our method outperforms baseline methods in geometric accuracy and visual fidelity, demonstrating a promising direction for future 3D generation models.

Community

Paper submitter

SyncHuman is a novel framework that combines 2D multiview and 3D native generative models to achieve high-quality, detailed, and structurally accurate 3D human reconstruction from a single image.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.07723 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.07723 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.07723 in a Space README.md to link it from this page.

Collections including this paper 1