解决3D纹理生成视角不一致问题，让不同角度看都自然连贯。
CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation
- 用几何校准注意力机制，让注意力聚焦在匹配的物体部分上。
- 生成纹理在多视角下保持一致，显著优于开源和商业模型。
- 适合需要高质量3D内容生成的研究者与工业用户。
尽管基于扩散模型取得了显著进展，当前的3D纹理生成系统仍受跨视角不一致的困扰——从某一视角看逼真的纹理在其他视角上常出现错位。我们发现该问题源于注意力模糊：对所有标记和模态无差别地应用全连接注意力，导致几何混淆和外观-结构耦合不稳定。为此，我们提出CaliTex框架，采用几何校准注意力，显式将注意力对齐于3D结构。其包含两个模块：部件对齐注意力（Part-Aligned Attention），强制语义匹配部件间的空间对齐；条件路由注意力（Condition-Routed Attention），通过几何条件路径传递外观信息以维持空间保真度。结合两阶段扩散变换器，使几何一致性成为网络的内在特性而非优化副产物。实验证明，CaliTex生成无缝且视角一致的纹理，优于各类开源与商业基线。
原文摘要 · Abstract (English)
Despite major advances brought by diffusion-based models, current 3D texture generation systems remain hindered by cross-view inconsistency -- textures that appear convincing from one viewpoint often fail to align across others. We find that this issue arises from attention ambiguity, where unstructured full attention is applied indiscriminately across tokens and modalities, causing geometric confusion and unstable appearance-structure coupling. To address this, we introduce CaliTex, a framework of geometry-calibrated attention that explicitly aligns attention with 3D structure. It introduces two modules: Part-Aligned Attention that enforces spatial alignment across semantically matched parts, and Condition-Routed Attention which routes appearance information through geometry-conditioned pathways to maintain spatial fidelity. Coupled with a two-stage diffusion transformer, CaliTex makes geometric coherence an inherent behavior of the network rather than a byproduct of optimization. Empirically, CaliTex produces seamless and view-consistent textures and outperforms both open-source and commercial baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。