LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bao, Jingzhi, Chen, Hongze, Zhu, Lingting, Liu, Chenyu, Zhang, Runze, Luo, Keyang, Hu, Zeyu, Chen, Weikai, Yin, Yingda, Wang, Xin, Lin, Zehong, Zhang, Jun, Han, Xiaoguang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918216647835648
author Bao, Jingzhi
Chen, Hongze
Zhu, Lingting
Liu, Chenyu
Zhang, Runze
Luo, Keyang
Hu, Zeyu
Chen, Weikai
Yin, Yingda
Wang, Xin
Lin, Zehong
Zhang, Jun
Han, Xiaoguang
author_facet Bao, Jingzhi
Chen, Hongze
Zhu, Lingting
Liu, Chenyu
Zhang, Runze
Luo, Keyang
Hu, Zeyu
Chen, Weikai
Yin, Yingda
Wang, Xin
Lin, Zehong
Zhang, Jun
Han, Xiaoguang
contents Physically-based rendering (PBR) provides a principled standard for realistic material-lighting interactions in computer graphics. Despite recent advances in generating PBR textures, existing methods fail to address two fundamental challenges: 1) materials decomposition from image prompts under limited illumination cues, and 2) seamless and view-consistent texture completion. To this end, we propose LumiTex, an end-to-end framework that comprises three key components: (1) a multi-branch generation scheme that disentangles albedo and metallic-roughness under shared illumination priors for robust material understanding, (2) a lighting-aware material attention mechanism that injects illumination context into the decoding process for physically grounded generation of albedo, metallic, and roughness maps, and (3) a geometry-guided inpainting module based on a large view synthesis model that enriches texture coverage and ensures seamless, view-consistent UV completion. Extensive experiments demonstrate that LumiTex achieves state-of-the-art performance in texture quality, surpassing both existing open-source and commercial methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19437
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
Bao, Jingzhi
Chen, Hongze
Zhu, Lingting
Liu, Chenyu
Zhang, Runze
Luo, Keyang
Hu, Zeyu
Chen, Weikai
Yin, Yingda
Wang, Xin
Lin, Zehong
Zhang, Jun
Han, Xiaoguang
Computer Vision and Pattern Recognition
Physically-based rendering (PBR) provides a principled standard for realistic material-lighting interactions in computer graphics. Despite recent advances in generating PBR textures, existing methods fail to address two fundamental challenges: 1) materials decomposition from image prompts under limited illumination cues, and 2) seamless and view-consistent texture completion. To this end, we propose LumiTex, an end-to-end framework that comprises three key components: (1) a multi-branch generation scheme that disentangles albedo and metallic-roughness under shared illumination priors for robust material understanding, (2) a lighting-aware material attention mechanism that injects illumination context into the decoding process for physically grounded generation of albedo, metallic, and roughness maps, and (3) a geometry-guided inpainting module based on a large view synthesis model that enriches texture coverage and ensures seamless, view-consistent UV completion. Extensive experiments demonstrate that LumiTex achieves state-of-the-art performance in texture quality, surpassing both existing open-source and commercial methods.
title LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.19437