通过模板引导的软信号学习融合语义几何特征，实现高效3D形状对应。
SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
- 用标准模板构建测地对应场，指导多模态特征学习
- 单次前向传播完成对应，精度超越现有方法且速度近实时
- 适合需要快速、鲁棒3D对应的应用场景
由于结构可变性、非等距变形和拓扑不一致，学习可变形3D形状之间的密集对应仍是长期挑战。现有方法通常在泛化能力、几何保真度和效率之间权衡。我们提出SGSoft，一种统一的内在流程：(i) 在标准模板上构建测地对应场；(ii) 利用预训练语义先验，以该测地对应场为监督，学习多模态密集描述子；(iii) 通过描述子空间中的最近邻搜索，在一次前向传播中检索密集对应。该框架在大幅姿态变化、结构差异和重网格化下仍能提供稳定且拓扑不变的监督。SGSoft在跨类别泛化上达到当前最优，同时在精度-效率权衡上优于以往方法。它无需预对齐、成对优化或后处理即可实现近实时推理。所学描述子可有效迁移至语义分割和形变传输等下游任务，建立了一种可扩展、可部署的密集3D对应范式。
原文摘要 · Abstract (English)
Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric fidelity, and efficiency. We address this by proposing SGSoft, a unified intrinsic pipeline that (i) constructs a geodesic correspondence field on a canonical template, (ii) learns multimodal dense descriptors guided by pretrained semantic priors with this geodesic correspondence field supervision, (iii) retrieves dense correspondences in a single feed-forward pass via nearest-neighbor search in descriptor space. This formulation enables stable and topology-invariant supervision under large pose variation, structural differences, and remeshing. SGSoft achieves state-of-the-art inter-category generalization while offering the best accuracy-efficiency trade-off among prior methods. It also achieves near real-time inference without pre-alignment, pairwise optimization, or post-refinement. Learned descriptors can be transferred effectively to downstream tasks such as semantic segmentation and deformation transfer, establishing a scalable and deployment-ready paradigm for dense 3D correspondence.
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。