Papers › CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

31 Dec 2020CVPR 2021 1arXiv:2012.15638archive 2025-07-28

Yiming Zeng, Yue Qian, Zhiyu Zhu, Junhui Hou, Hui Yuan, Ying He

Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -- the first unsupervised and end-to-end deep learning-based framework -- to drive the learning of dense correspondence between 3D shapes by means of deformation-like reconstruction to overcome the need for annotated data. Specifically, CorrNet3D consists of a deep feature embedding module and two novel modules called correspondence indicator and symmetric deformer. Feeding a pair of raw point clouds, our model first learns the pointwise features and passes them into the indicator to generate a learnable correspondence matrix used to permute the input pair. The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence. The extensive experiments on both synthetic and real-world datasets of rigid and non-rigid 3D shapes show our CorrNet3D outperforms state-of-the-art methods to a large extent, including those taking meshes as input. CorrNet3D is a flexible framework in that it can be easily adapted to supervised learning if annotated data are available. The source code and pre-trained model will be available at https://github.com/ZENGYIMING-EAMON/CorrNet3D.git.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ZENGYIMING-EAMON/CorrNet3D officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Dense Shape Correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Dense Shape Correspondence SHREC'19 CorrNet3D (Trained on Surreal) Accuracy at 1% 6.0 #7 of 11 Archive leaderboard report
3D Dense Shape Correspondence SHREC'19 CorrNet3D (Trained on Surreal) Euclidean Mean Error (EME) 6.9 #7 of 11 Archive leaderboard report
3D Dense Shape Correspondence SHREC'19 CorrNet3D Accuracy at 1% 0.4 #11 of 11 Archive leaderboard report
3D Dense Shape Correspondence SHREC'19 CorrNet3D Euclidean Mean Error (EME) 33.8 #11 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections