Paper Overview
Field: Computer Vision Authors: Jaeyeong Kim, Jinhyuk Jang, Jongmin Lee, Kyehong Park, Seungryong Kim arXiv: 2610.10539
Abstract
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 pairwise physical relationship annotations. Comprehensive experiments show that Tetris3D recovers coherent object shapes and poses even when interaction regions are occluded, achieving state-of-the-art performance in both generation quality and physical stability.
Key Contributions
- Explicit inter-object conditioning: each object's generation is conditioned on surrounding geometry and physical relationships, rather than treating objects independently.
- ComOb dataset: a physics simulation-based dataset of 1.2M scenes with per-object meshes and pairwise physical relationship annotations.
- Strong results: coherent shape and pose recovery even with occluded interaction regions; state-of-the-art generation quality and physical stability.