DiffTex: Differentiable Texturing for Architectural Proxy Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiong, Weidan, Wu, Yongli, Zeng, Bochuan, Guo, Jianwei, Lischinski, Dani, Cohen-Or, Daniel, Huang, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914066618908672
author Xiong, Weidan
Wu, Yongli
Zeng, Bochuan
Guo, Jianwei
Lischinski, Dani
Cohen-Or, Daniel
Huang, Hui
author_facet Xiong, Weidan
Wu, Yongli
Zeng, Bochuan
Guo, Jianwei
Lischinski, Dani
Cohen-Or, Daniel
Huang, Hui
contents Simplified proxy models are commonly used to represent architectural structures, reducing storage requirements and enabling real-time rendering. However, the geometric simplifications inherent in proxies result in a loss of fine color and geometric details, making it essential for textures to compensate for the loss. Preserving the rich texture information from the original dense architectural reconstructions remains a daunting task, particularly when working with unordered RGB photographs. We propose an automated method for generating realistic texture maps for architectural proxy models at the texel level from an unordered collection of registered photographs. Our approach establishes correspondences between texels on a UV map and pixels in the input images, with each texel's color computed as a weighted blend of associated pixel values. Using differentiable rendering, we optimize blending parameters to ensure photometric and perspective consistency, while maintaining seamless texture coherence. Experimental results demonstrate the effectiveness and robustness of our method across diverse architectural models and varying photographic conditions, enabling the creation of high-quality textures that preserve visual fidelity and structural detail.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23336
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffTex: Differentiable Texturing for Architectural Proxy Models
Xiong, Weidan
Wu, Yongli
Zeng, Bochuan
Guo, Jianwei
Lischinski, Dani
Cohen-Or, Daniel
Huang, Hui
Graphics
Computer Vision and Pattern Recognition
Simplified proxy models are commonly used to represent architectural structures, reducing storage requirements and enabling real-time rendering. However, the geometric simplifications inherent in proxies result in a loss of fine color and geometric details, making it essential for textures to compensate for the loss. Preserving the rich texture information from the original dense architectural reconstructions remains a daunting task, particularly when working with unordered RGB photographs. We propose an automated method for generating realistic texture maps for architectural proxy models at the texel level from an unordered collection of registered photographs. Our approach establishes correspondences between texels on a UV map and pixels in the input images, with each texel's color computed as a weighted blend of associated pixel values. Using differentiable rendering, we optimize blending parameters to ensure photometric and perspective consistency, while maintaining seamless texture coherence. Experimental results demonstrate the effectiveness and robustness of our method across diverse architectural models and varying photographic conditions, enabling the creation of high-quality textures that preserve visual fidelity and structural detail.
title DiffTex: Differentiable Texturing for Architectural Proxy Models
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23336