Robust Context Modeling for Unsupervised Non-Rigid Point Cloud Correspondence
- 16 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7526-7539
Abstract
We address the “long-range ambiguity” problem for unsupervised non-rigid point cloud correspondence, where corresponding points own inconsistent features while different local regions are spatially or geometrically similar. Previous methods struggle with this problem, since local reference frames (LRF) or coordinate-based methods struggle to exclude locally similar or spatially near mismatches, and widely used independent geometric relations might be inconsistent under non-rigid deformation, introducing extra ambiguity. To this end, we propose a novel robust context modeling module (RCM) to alleviate long-range ambiguity in two aspects: 1) RCM tackles the ambiguity problem by introducing inter-relation attention (IRA), which mines robust cues from the interplay between relative geometric relations. 2) RCM enhances features with accessible long-range information from IRAs, following a local-to-global manner. Our method shows significant improvements in multiple benchmarks, with accurate correspondence over rotation and large deformation perturbation. Specifically, our method achieves a new state-of-the-art performance with correspondence accuracy of 33.9% and mean error of 4.2 on the SURREAL benchmark.Keywords
Funding Information
- National Natural Science Foundation of China (62372377)
- National Natural Science Foundation of China (2025AFB832)
This publication has 43 references indexed in Scilit:
- DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction2021
- PREDATOR: Registration of 3D Point Clouds with Low Overlap2021
- CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds2021
- RPM-Net: Robust Point Matching Using Learned Features2020
- Unsupervised Learning of Dense Shape Correspondence2019
- 3D-CODED: 3D Correspondences by Deep Deformation2018
- 3D Menagerie: Modeling the 3D Shape and Pose of Animals2017
- 3D ShapeNets: A deep representation for volumetric shapes2015
- K-Nearest Neighbors2013
- Numerical Geometry of Non-Rigid Shapes2009