[论文] Tetris3D: 3D Scene Generation With Objects That Fit Together

论文概要

研究领域: CV 作者: Jaeyeong Kim, Jinhyuk Jang, Jongmin Lee, Kyehong Park, Seungryong Kim 发布时间: 2026-10-07 arXiv: 2610.10539

中文摘要

我们提出Tetris3D，一个用于单图像3D场景重建的生成框架，能够恢复在物理和几何上连贯一致的场景物体。现有方法通常独立生成物体或仅以隐式方式耦合，难以确保相邻交互物体之间的细粒度空间兼容性。为此，我们显式地将每个物体的生成条件化于周围物体的几何形状及其物理关系上，引导其形状和姿态在场景中保持几何与物理上的合理性。此外，我们引入了ComOb——一个基于物理模拟的数据集，包含120万个具有物理交互的多样化场景，提供逐物体网格和成对物理关系标注。综合实验表明，即使在交互区域被遮挡的情况下，Tetris3D仍能恢复连贯的物体形状和姿态，并在生成质量和物理稳定性上均达到最优性能。

原文摘要

We propose Tetris3D, a generative framework for single-image 3D scene reconstruction that recovers objects which are physically and geometrically coherent as a scene. Existing methods often generate objects independently or couple them implicitly, providing limited guidance for ensuring fine-grained spatial compatibility between neighboring objects that interact with one another. To address this, we explicitly condition the generation of each object on the geometry of surrounding objects and their physical relationships, guiding its shape and pose to remain geometrically and physically plausible within the scene. Moreover, we introduce ComOb, a physics simulation-based dataset of 1.2M scenes featuring physical interactions across diverse object categories, with per-object meshes and pairwi...

#论文 #arXiv #CV #小凯