面向无监督非刚性点云对应的拓扑感知特征传播
Topology-aware Feature Propagation for Unsupervised Non-rigid Point Cloud Correspondence
用拓扑感知的超点特征传播替代基于空间近邻的传播，并用向量量化码本增强特征以抵抗形状差异，可直接迁移到非刚性配准、形变跟踪与点云对应任务的特征提取环节。
原文依据 we estimate keypoints as superpoints and encode superpoint features with topology weights
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无监督非刚性点云对应旨在无标注条件下预测点对点对应关系。现有方法采用基于空间关系的特征传播策略，其中包含非物理连接，对非刚性形变较为敏感。为解决该问题，我们主张学习对非刚性形变鲁棒的形状拓扑，并提出拓扑感知特征传播模块，将其集成到由粗到细的传播与优化流程中。为提取对非刚性形变鲁棒的点特征，我们将关键点估计为超点，并以拓扑权重编码超点特征，从而在非刚性形变下学习到合理的拓扑结构。利用向量量化码本，以在整个数据集上存储的代表性特征增强原始超点特征，提升特征对形状差异的鲁棒性。经过由粗到细的特征融合与高效的测试时优化，可获得鲁棒的点对点对应关系。在多个基准上的大量实验表明，本方法达到了最优性能。
英文原文摘要 1143 字符
Unsupervised non-rigid point cloud correspondence aims to predict point-to-point correspondences without annotations. Existing methods leverage the spatial-relation-based feature propagation strategy that includes non-physical connections, which are sensitive to non-rigid deformation. To address this issue, we advocate to learn shape topology robust to non-rigid deformation, and propose the topology-aware feature propagation module integrated into a coarse-to-fine propagation and optimization pipeline. To extract point features robust to non-rigid deformation, we estimate keypoints as superpoints and encode superpoint features with topology weights, which learns reasonable topologies under non-rigid deformation. The vector quantization codebook is leveraged to enhance the original superpoint features with stored representative features across the dataset, improving feature robustness against shape variance. Robust point-wise correspondence is yielded after coarse-to-fine feature fusion and efficient test-time optimization. Extensive experiments on multiple benchmarks demonstrate the state-of-the-art performance of our method.