Papers
arxiv:2408.13499

R2G: Reasoning to Ground in 3D Scenes

Published on Aug 24, 2024
Authors:
,
,

Abstract

R2G, a neural symbolic model using a semantic concept-based scene graph, grounds target objects within 3D scenes with improved interpretability through recurrent attention transfer.

AI-generated summary

We propose Reasoning to Ground (R2G), a neural symbolic model that grounds the target objects within 3D scenes in a reasoning manner. In contrast to prior works, R2G explicitly models the 3D scene with a semantic concept-based scene graph; recurrently simulates the attention transferring across object entities; thus makes the process of grounding the target objects with the highest probability interpretable. Specifically, we respectively embed multiple object properties within the graph nodes and spatial relations among entities within the edges, utilizing a predefined semantic vocabulary. To guide attention transferring, we employ learning or prompting-based methods to analyze the referential utterance and convert it into reasoning instructions within the same semantic space. In each reasoning round, R2G either (1) merges current attention distribution with the similarity between the instruction and embedded entity properties or (2) shifts the attention across the scene graph based on the similarity between the instruction and embedded spatial relations. The experiments on Sr3D/Nr3D benchmarks show that R2G achieves a comparable result with the prior works while maintaining improved interpretability, breaking a new path for 3D language grounding.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2408.13499 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/2408.13499 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/2408.13499 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.