Preprint
Oct 2026
Learning to Code the World: Harness Evolution for Compositional 3D Reconstruction
Reconstructing editable and compositional 3D scenes from a real image requires jointly reasoning about geometry, object structure, and spatial relationships. We introduce SceneEvolve, a framework that represents 3D scenes as executable code and improves reconstruction by evolving the harness around a small open-source...
Hao-Yu Yao, Chen-Guo Lin, Rui-Ze Du et al.
· 0 citations