Research
Luce: Relightable Gaussians for 3D Asset Generation
High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representatio
High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representation should include physically based rendering (PBR) modalities such as albedo, metallic-roughness, and surface normals. We propose Luce, a 3D representation that unifies geometry and PBR materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for each modality. A variational autoencoder compresses this representation into a unified material-aware latent space. A…
Related
- ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation
- Effective Gaussian Management for High-fidelity Scene Reconstruction
- Velox: Learning Representations of 4D Geometry and Appearance
- Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design
Source: Apple ML Research | 2026-08-26