Research

Paper

AI LLM March 17, 2026

VideoMatGen: PBR Materials through Joint Generative Modeling

Authors

Jon Hasselgren, Zheng Zeng, Milos Hasan, Jacob Munkberg

Abstract

We present a method for generating physically-based materials for 3D shapes based on a video diffusion transformer architecture. Our method is conditioned on input geometry and a text description, and jointly models multiple material properties (base color, roughness, metallicity, height map) to form physically plausible materials. We further introduce a custom variational auto-encoder which encodes multiple material modalities into a compact latent space, which enables joint generation of multiple modalities without increasing the number of tokens. Our pipeline generates high-quality materials for 3D shapes given a text prompt, compatible with common content creation tools.

Metadata

arXiv ID: 2603.16566
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16566v1</id>\n    <title>VideoMatGen: PBR Materials through Joint Generative Modeling</title>\n    <updated>2026-03-17T14:24:20Z</updated>\n    <link href='https://arxiv.org/abs/2603.16566v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16566v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We present a method for generating physically-based materials for 3D shapes based on a video diffusion transformer architecture. Our method is conditioned on input geometry and a text description, and jointly models multiple material properties (base color, roughness, metallicity, height map) to form physically plausible materials. We further introduce a custom variational auto-encoder which encodes multiple material modalities into a compact latent space, which enables joint generation of multiple modalities without increasing the number of tokens. Our pipeline generates high-quality materials for 3D shapes given a text prompt, compatible with common content creation tools.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.GR'/>\n    <published>2026-03-17T14:24:20Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Jon Hasselgren</name>\n    </author>\n    <author>\n      <name>Zheng Zeng</name>\n    </author>\n    <author>\n      <name>Milos Hasan</name>\n    </author>\n    <author>\n      <name>Jacob Munkberg</name>\n    </author>\n  </entry>"
}