TRELLIS.2: Native and Compact Structured Latents for 3D Generation

microsoft.github.io · 548 words · saved by 2 readers

Our 4B-parameter model generates high-resolution fully textured assets with exceptional fidelity and efficiency with vanilla DiTs. At the core is the native and compact structured latents, which push the frontiers of fidelity and compactness at the same time. Reconstruction accuracy v.s. Latent compactness Our method robustly handles complex structures, including open surfaces, non-manifold geometry, and enclosed interior structures, breaking the constraints of iso-surface fields. Our method can model arbitrary surface attributes such as Base Color, Roughness, Metallic, and Opacity (i.e., Transparency or Alpha channel), enabling Physically Based Rendering (PBR) and photorealistic relighting. Data processing for training and inferenc

Key Features High Quality, Resolution, Efficiency Arbitrary Topology Rich Texture Minimalist Asset Processing High Quality, Resolution & Efficiency Our 4B-parameter model generates high-resolution fully textured assets with exceptional fidelity and efficiency with vanilla DiTs. 3s (2s+1s) 5123 resolution 17s (10s+7s) 10243 resolution 60s (35s+25s) 15363 resolution * Total generation time (shape + material). ** Tested with NVIDIA H100 GPU. At the core is the native and compact structured latents, which push the frontiers of fidelity and compactness at the same time.…

TRELLIS.2: Native and Compact Structured Latents for 3D Generation

saved by

related reading