VideoMatGen: PBR Materials through Joint Generative Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hasselgren, Jon, Zeng, Zheng, Hasan, Milos, Munkberg, Jacob
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912971060412416
author Hasselgren, Jon
Zeng, Zheng
Hasan, Milos
Munkberg, Jacob
author_facet Hasselgren, Jon
Zeng, Zheng
Hasan, Milos
Munkberg, Jacob
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16566
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VideoMatGen: PBR Materials through Joint Generative Modeling
Hasselgren, Jon
Zeng, Zheng
Hasan, Milos
Munkberg, Jacob
Computer Vision and Pattern Recognition
Graphics
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.
title VideoMatGen: PBR Materials through Joint Generative Modeling
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2603.16566