About this paper
UltraTex employs a cascaded multi-view framework that integrates physical knowledge and vision-language model features to accurately generate physically plausible PBR texture maps.
Generating physically based rendering (PBR) texture maps for a 3D mesh from a single reference image is highly ambiguous, as the observed appearance entangles material identity, surface reflectance, and illumination. While current generative methods produce realistic albedo maps, they still struggle to infer accurate metallic and roughness attributes for relighting. We present UltraTex, a cascaded multi-view framework that moves beyond appearance matching by integrating physical knowledge into multi-view diffusion-based PBR generation. UltraTex first jointly predicts albedo and world-space shading normals to generate more detailed albedo maps, and then predicts metallic-roughness (MR) maps…
cascaded multi-view frameworkmulti-view diffusion-based PBR generationalbedo mapsworld-space shading normalsmetallic-roughness (MR) mapsmaterial semantic priorslightweight adaptervision-language model (VLM)intrinsic material representation tokensphotometric representation alignment
- Upvotes
- 2
- Authors
- 5
- Published
- Nov 18, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
UltraTex: Aligning Physical Knowledge for High-Fidelity PBR Texture Generation was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 11 checks on 2 different days. Its best position was #22 of 30, reached on Nov 19, 13:29 UTC. It dropped off the list after Nov 20, 05:29 UTC.