用分层神经语义表示实现3D语义对应，无需训练且泛化能力强。
Hierarchical Neural Semantic Representation for 3D Semantic Correspondence
- 分层表示融合全局语义与多分辨率局部几何特征
- 从粗到细迭代匹配，提升对应准确性与一致性
- 免训练适配多种生成模型，跨类别也表现佳
本文提出一种基于分层神经语义表示（HNSR）的新方法，用于估计精确且鲁棒的3D语义对应。首先，HNSR结合预训练3D生成模型中的3D先验，设计了全局语义特征以捕捉高层结构，并通过多分辨率局部几何特征保留细节。其次，提出渐进式从全局到局部的匹配策略：先用全局特征建立粗粒度语义对应，再逐轮利用局部几何特征进行细化，获得高精度且语义一致的映射。第三，该框架无需训练，可广泛兼容各类预训练3D生成骨干网络，在不同形状类别间展现出强泛化能力。方法支持形状共分割、关键点匹配、纹理迁移等多种应用，跨类别场景下仍表现良好。定性和定量评估均表明，本方法优于现有最先进技术。
原文摘要 · Abstract (English)
This paper presents a new approach to estimate accurate and robust 3D semantic correspondence with the hierarchical neural semantic representation. Our work has three key contributions. First, we design the hierarchical neural semantic representation (HNSR), which consists of a global semantic feature to capture high-level structure and multi-resolution local geometric features to preserve fine details, by carefully harnessing 3D priors from pre-trained 3D generative models. Second, we design a progressive global-to-local matching strategy, which establishes coarse semantic correspondence using the global semantic feature, then iteratively refines it with local geometric features, yielding accurate and semantically-consistent mappings. Third, our framework is training-free and broadly compatible with various pre-trained 3D generative backbones, demonstrating strong generalization across diverse shape categories. Our method also supports various applications, such as shape co-segmentation, keypoint matching, and texture transfer, and generalizes well to structurally diverse shapes, with promising results even in cross-category scenarios. Both qualitative and quantitative evaluations show that our method outperforms previous state-of-the-art techniques.
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。