NI-Tex: Non-isometric Image-based Garment Texture Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shan, Hui, Li, Ming, Yang, Haitao, Zheng, Kai, Zheng, Sizhe, Fu, Yanwei, Huang, Xiangru
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914389541519360
author Shan, Hui
Li, Ming
Yang, Haitao
Zheng, Kai
Zheng, Sizhe
Fu, Yanwei
Huang, Xiangru
author_facet Shan, Hui
Li, Ming
Yang, Haitao
Zheng, Kai
Zheng, Sizhe
Fu, Yanwei
Huang, Xiangru
contents Existing industrial 3D garment meshes already cover most real-world clothing geometries, yet their texture diversity remains limited. To acquire more realistic textures, generative methods are often used to extract Physically-based Rendering (PBR) textures and materials from large collections of wild images and project them back onto garment meshes. However, most image-conditioned texture generation approaches require strict topological consistency between the input image and the input 3D mesh, or rely on accurate mesh deformation to match to the image poses, which significantly constrains the texture generation quality and flexibility. To address the challenging problem of non-isometric image-based garment texture generation, we construct 3D Garment Videos, a physically simulated, garment-centric dataset that provides consistent geometry and material supervision across diverse deformations, enabling robust cross-pose texture learning. We further employ Nano Banana for high-quality non-isometric image editing, achieving reliable cross-topology texture generation between non-isometric image-geometry pairs. Finally, we propose an iterative baking method via uncertainty-guided view selection and reweighting that fuses multi-view predictions into seamless, production-ready PBR textures. Through extensive experiments, we demonstrate that our feedforward dual-branch architecture generates versatile and spatially aligned PBR materials suitable for industry-level 3D garment design.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18765
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NI-Tex: Non-isometric Image-based Garment Texture Generation
Shan, Hui
Li, Ming
Yang, Haitao
Zheng, Kai
Zheng, Sizhe
Fu, Yanwei
Huang, Xiangru
Computer Vision and Pattern Recognition
Artificial Intelligence
Existing industrial 3D garment meshes already cover most real-world clothing geometries, yet their texture diversity remains limited. To acquire more realistic textures, generative methods are often used to extract Physically-based Rendering (PBR) textures and materials from large collections of wild images and project them back onto garment meshes. However, most image-conditioned texture generation approaches require strict topological consistency between the input image and the input 3D mesh, or rely on accurate mesh deformation to match to the image poses, which significantly constrains the texture generation quality and flexibility. To address the challenging problem of non-isometric image-based garment texture generation, we construct 3D Garment Videos, a physically simulated, garment-centric dataset that provides consistent geometry and material supervision across diverse deformations, enabling robust cross-pose texture learning. We further employ Nano Banana for high-quality non-isometric image editing, achieving reliable cross-topology texture generation between non-isometric image-geometry pairs. Finally, we propose an iterative baking method via uncertainty-guided view selection and reweighting that fuses multi-view predictions into seamless, production-ready PBR textures. Through extensive experiments, we demonstrate that our feedforward dual-branch architecture generates versatile and spatially aligned PBR materials suitable for industry-level 3D garment design.
title NI-Tex: Non-isometric Image-based Garment Texture Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.18765