跳到正文
返回论文列表
cs.GR提交于 已译

FlexPainter: 灵活且多视角一致的纹理生成

FlexPainter: Flexible and Multi-View Consistent Texture Generation

Dongyu Yan · Leyi Wu · Jiantao Lin · Luozhou Wang · Tianshuo Xu · Zhifei Chen · et al.

中文摘要

纹理贴图制作是3D建模的关键环节,决定渲染质量。基于扩散模型的方法为纹理生成提供了新路径,但受控灵活性低和提示模态有限限制了创作者发挥,且多视角图像不一致常导致纹理质量差。FlexPainter 是一种新型纹理生成流水线,支持灵活的多模态条件引导并实现高一致性纹理生成。该方法构建共享条件嵌入空间以聚合不同输入模态,利用基于图像的CFG方法分解结构与风格信息实现参考图风格化。借助图像扩散先验中的3D知识,通过网格表示同时生成多视角图像以增强全局理解,并在扩散采样中引入视角同步与自适应加权模块确保局部一致性。最后,结合3D感知纹理补全与增强模型生成无缝高分辨率纹理贴图。实验表明,该框架在灵活性和生成质量上显著优于现有最先进方法。

关键要点

  1. 01现有扩散方法存在控制灵活性低、提示模态有限及多视角图像不一致导致纹理质量差的问题。
  2. 02构建共享条件嵌入空间聚合多模态输入,利用基于图像的CFG方法分解结构与风格信息实现风格化。
  3. 03采用网格表示同时生成多视角图像,结合视角同步与自适应加权模块确保局部一致性。
  4. 04结合3D感知纹理补全与增强模型,最终生成无缝且高分辨率的纹理贴图。
  5. 05综合实验证明,FlexPainter 在灵活性和生成质量上显著优于当前最先进方法。

解读

尚无解读。

原始英文摘要

arXiv:2506.02620v2 Announce Type: replace-cross Abstract: 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.

同方向论文 · cs.GR

查看全部 →