MatLat: Material Latent Space for PBR Texture Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yeo, Kyeongmin, Min, Yunhong, Kim, Jaihoon, Sung, Minhyuk
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915686150832128
author Yeo, Kyeongmin
Min, Yunhong
Kim, Jaihoon
Sung, Minhyuk
author_facet Yeo, Kyeongmin
Min, Yunhong
Kim, Jaihoon
Sung, Minhyuk
contents We propose a generative framework for producing high-quality PBR textures on a given 3D mesh. As large-scale PBR texture datasets are scarce, our approach focuses on effectively leveraging the embedding space and diffusion priors of pretrained latent image generative models while learning a material latent space, MatLat, through targeted fine-tuning. Unlike prior methods that freeze the embedding network and thus lead to distribution shifts when encoding additional PBR channels and hinder subsequent diffusion training, we fine-tune the pretrained VAE so that new material channels can be incorporated with minimal latent distribution deviation. We further show that correspondence-aware attention alone is insufficient for cross-view consistency unless the latent-to-image mapping preserves locality. To enforce this locality, we introduce a regularization in the VAE fine-tuning that crops latent patches, decodes them, and aligns the corresponding image regions to maintain strong pixel-latent spatial correspondence. Ablation studies and comparison with previous baselines demonstrate that our framework improves PBR texture fidelity and that each component is critical for achieving state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17302
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MatLat: Material Latent Space for PBR Texture Generation
Yeo, Kyeongmin
Min, Yunhong
Kim, Jaihoon
Sung, Minhyuk
Computer Vision and Pattern Recognition
We propose a generative framework for producing high-quality PBR textures on a given 3D mesh. As large-scale PBR texture datasets are scarce, our approach focuses on effectively leveraging the embedding space and diffusion priors of pretrained latent image generative models while learning a material latent space, MatLat, through targeted fine-tuning. Unlike prior methods that freeze the embedding network and thus lead to distribution shifts when encoding additional PBR channels and hinder subsequent diffusion training, we fine-tune the pretrained VAE so that new material channels can be incorporated with minimal latent distribution deviation. We further show that correspondence-aware attention alone is insufficient for cross-view consistency unless the latent-to-image mapping preserves locality. To enforce this locality, we introduce a regularization in the VAE fine-tuning that crops latent patches, decodes them, and aligns the corresponding image regions to maintain strong pixel-latent spatial correspondence. Ablation studies and comparison with previous baselines demonstrate that our framework improves PBR texture fidelity and that each component is critical for achieving state-of-the-art performance.
title MatLat: Material Latent Space for PBR Texture Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.17302