Toys4K

Researchers propose Luce, a 3D representation that unifies geometry and PBR materials in a voxelized multimodal Gaussian cloud, enabling relightable image-to-3D generation. On Toys4K, Luce improves FI…

Axolotl3D, a multi-modal and occlusion-aware 3D generation model introduced in arXiv:2607.20660v1, jointly conditions on images, visibility masks, camera parameters, and a partial point cloud to enabl…

Researchers have developed a training-free method for 3D shape abstraction using generative image models, achieving state-of-the-art Chamfer distance on HumanPrim and Toys4K benchmarks with 5-9 primit…