FlexPainter: Flexible and Multi-View Consistent Texture Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Dongyu, Wu, Leyi, Lin, Jiantao, Wang, Luozhou, Xu, Tianshuo, Chen, Zhifei, Yang, Zhen, Xu, Lie, Zhang, Shunsi, Chen, Yingcong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915320965365760
author Yan, Dongyu
Wu, Leyi
Lin, Jiantao
Wang, Luozhou
Xu, Tianshuo
Chen, Zhifei
Yang, Zhen
Xu, Lie
Zhang, Shunsi
Chen, Yingcong
author_facet Yan, Dongyu
Wu, Leyi
Lin, Jiantao
Wang, Luozhou
Xu, Tianshuo
Chen, Zhifei
Yang, Zhen
Xu, Lie
Zhang, Shunsi
Chen, Yingcong
contents Texture map production is an important part of 3D modeling and determines the rendering quality. Recently, diffusion-based methods have opened a new way for texture generation. However, restricted control flexibility and limited prompt modalities may prevent creators from producing desired results. Furthermore, inconsistencies between generated multi-view images often lead to poor texture generation quality. To address these issues, we introduce \textbf{FlexPainter}, a novel texture generation pipeline that enables flexible multi-modal conditional guidance and achieves highly consistent texture generation. A shared conditional embedding space is constructed to perform flexible aggregation between different input modalities. Utilizing such embedding space, we present an image-based CFG method to decompose structural and style information, achieving reference image-based stylization. Leveraging the 3D knowledge within the image diffusion prior, we first generate multi-view images simultaneously using a grid representation to enhance global understanding. Meanwhile, we propose a view synchronization and adaptive weighting module during diffusion sampling to further ensure local consistency. Finally, a 3D-aware texture completion model combined with a texture enhancement model is used to generate seamless, high-resolution texture maps. Comprehensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods in both flexibility and generation quality.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlexPainter: Flexible and Multi-View Consistent Texture Generation
Yan, Dongyu
Wu, Leyi
Lin, Jiantao
Wang, Luozhou
Xu, Tianshuo
Chen, Zhifei
Yang, Zhen
Xu, Lie
Zhang, Shunsi
Chen, Yingcong
Graphics
Computer Vision and Pattern Recognition
Texture map production is an important part of 3D modeling and determines the rendering quality. Recently, diffusion-based methods have opened a new way for texture generation. However, restricted control flexibility and limited prompt modalities may prevent creators from producing desired results. Furthermore, inconsistencies between generated multi-view images often lead to poor texture generation quality. To address these issues, we introduce \textbf{FlexPainter}, a novel texture generation pipeline that enables flexible multi-modal conditional guidance and achieves highly consistent texture generation. A shared conditional embedding space is constructed to perform flexible aggregation between different input modalities. Utilizing such embedding space, we present an image-based CFG method to decompose structural and style information, achieving reference image-based stylization. Leveraging the 3D knowledge within the image diffusion prior, we first generate multi-view images simultaneously using a grid representation to enhance global understanding. Meanwhile, we propose a view synchronization and adaptive weighting module during diffusion sampling to further ensure local consistency. Finally, a 3D-aware texture completion model combined with a texture enhancement model is used to generate seamless, high-resolution texture maps. Comprehensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods in both flexibility and generation quality.
title FlexPainter: Flexible and Multi-View Consistent Texture Generation
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.02620