Munkberg, JacobWang, ZianLiang, RuofanShen, TianchangHasselgren, JonWang, BeibeiWilkie, Alexander2025-06-202025-06-2020251467-8659https://doi.org/10.1111/cgf.70180https://diglib.eg.org/handle/10.1111/cgf70180We leverage finetuned video diffusion models, intrinsic decomposition of videos, and physically-based differentiable rendering to generate high quality materials for 3D models given a text prompt or a single image. We condition a video diffusion model to respect the input geometry and lighting condition. This model produces multiple views of a given 3D model with coherent material properties. Secondly, we use a recent model to extract intrinsics (base color, roughness, metallic) from the generated video. Finally, we use the intrinsics alongside the generated video in a differentiable path tracer to robustly extract PBR materials directly compatible with common content creation tools.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Appearance and texture representations; Ray tracing; Reflectance modelingComputing methodologies → Appearance and texture representationsRay tracingReflectance modeling10.1111/cgf.7018010 pages