REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image 文章

ArXiv CS.CV2026-05-29NEWSen作者: Xiaoxuan Ma, Jiashun Wang, Nicolas Ugrinovic, Yehonathan Litman, Kris Kitani

摘要

arXiv:2605.30338v1 Announce Type: new Abstract: Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applications such as immersive interaction and content creation. However, existing single-image reconstruction methods fall short in capturing the physical structure of a scene. As a result, they often produce geometrically plausible but physically inconsistent results, including object floating and penetration, which lead to unstable behavior in physics simulations. Image-conditioned scene generation methods improve physical plausibility but often rely on strong scene priors, yielding plausible yet inaccurate object arrangements that fail to match the input image. We propose REST3D, a single-image reconstruction framework that can reconstruct physically stable 3D scenes by integrating physical scene understanding with physics-constrained refinement.

相关公司

暂无数据

相关人物

暂无数据

相关技术

暂无数据