Tetris3D generates physically coherent 3D scenes from a single image
An arXiv paper introduces Tetris3D, a generative framework for single-image 3D scene reconstruction that explicitly conditions each object's generation on the geometry and physical relationships of surrounding objects, keeping shape and pose geometrically and physically plausible within the scene. The authors report that Tetris3D recovers coherent object shapes and poses even when interacting regions are occluded, and achieves state-of-the-art results in generation quality and physical stability. The work also releases ComOb, a physics-simulation-based dataset of 1.2M scenes with per-object meshes and pairwise physical relation annotations.
If reproducible, explicitly modelling physical relations between objects could reduce the interpenetration and floating artefacts common in single-image 3D scene reconstruction.