Luce: Relightable Gaussians for 3D Asset Generation

Apple Machine LearningAugust 26, 2026en

Apple Machine Learning

AI Global Wire

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…

This is a short summary published by AI Global Wire. The full article is owned and hosted by Apple Machine Learning — open it there to read it in full.

• Verktyg
• Bild