GLASS: 图与视觉-语言辅助的语义形状对应
GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence
AI总结：
GLASS通过整合几何频谱分析与视觉-语言模型的语义先验，实现了在非等距变形和跨类设置中鲁棒的3D形状语义对应学习。
摘要：
在3D形状之间建立密集对应关系对于基础下游任务至关重要，包括纹理传输、形状插值和机器人操作。然而，学习这些映射而无需手动监督仍是一个严峻的挑战，尤其是在严重的非等距变形和跨类设置中，其中几何线索是模糊的。传统功能图方法虽然优雅，但通常在这些情况下表现不佳，因为它们依赖于等距性。为了解决这个问题，我们提出了GLASS，一种框架，通过将几何频谱分析与来自视觉-语言基础模型的丰富语义先验相结合，弥合了这一差距。GLASS引入了三个关键创新：(i) 一种视图一致的策略，使能够从强大的视觉基础模型中稳健地提取多视图视觉特征；(ii) 通过零样本3D分割将语言嵌入注入到顶点描述符中，捕捉高层次的部分语义；(iii) 一种图辅助对比损失，通过利用区域之间的测地线和拓扑关系来强制区域之间的结构一致性（例如，源的头部'' ↔ 目标头部''）。这种设计使GLASS能够在没有地面真相监督的情况下学习全局一致且语义一致的映射。广泛的实验表明，GLASS在所有情况下都实现了最先进的性能，保持了在标准近等距任务上的高精度，同时在具有挑战性的设置中显著提高了性能。具体而言，它在跨类基准SNIS和非等距基准SMAL和TOPKIDS上分别实现了平均测地线误差为0.21、4.5和5.6，比URSSM基线的0.49、6.0和8.9分别减少了57%、25%和37%。
英文摘要：
Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However, learning these mappings without manual supervision remains a formidable challenge, particularly under severe non-isometric deformations and in inter-class settings where geometric cues are ambiguous. Conventional functional map methods, while elegant, typically struggle in these regimes due to their reliance on isometry. To address this, we present GLASS, a framework that bridges the gap by integrating geometric spectral analysis with rich semantic priors from vision-language foundation models. GLASS introduces three key innovations: (i) a view-consistent strategy that enables robust multi-view visual feature extraction from powerful vision foundation models; (ii) the injection of language embeddings into vertex descriptors via zero-shot 3D segmentation, capturing high-level part semantics; and (iii) a graph-assisted contrastive loss that enforces structural consistency between regions (e.g., source's head'' $\leftrightarrow$ target's head'') by leveraging geodesic and topological relationships between regions. This design allows GLASS to learn globally coherent and semantically consistent maps without ground-truth supervision. Extensive experiments demonstrate that GLASS achieves state-of-the-art performance across all regimes, maintaining high accuracy on standard near-isometric tasks while significantly advancing performance in challenging settings. Specifically, it achieves average geodesic errors of 0.21, 4.5, and 5.6 on the inter-class benchmark SNIS and non-isometric benchmarks SMAL and TOPKIDS, reducing errors from URSSM baselines of 0.49, 6.0, and 8.9 by 57%, 25%, and 37%, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
