Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence

About

Unsupervised point cloud shape correspondence aims to obtain dense point-to-point correspondences between point clouds without manually annotated pairs. However, humans and some animals have bilateral symmetry and various orientations, which lead to severe mispredictions of symmetrical parts. Besides, point cloud noise disrupts consistent representations for point cloud and thus degrades the shape correspondence accuracy. To address the above issues, we propose a Self-Ensembling ORientation-aware Network termed SE-ORNet. The key of our approach is to exploit an orientation estimation module with a domain adaptive discriminator to align the orientations of point cloud pairs, which significantly alleviates the mispredictions of symmetrical parts. Additionally, we design a selfensembling framework for unsupervised point cloud shape correspondence. In this framework, the disturbances of point cloud noise are overcome by perturbing the inputs of the student and teacher networks with different data augmentations and constraining the consistency of predictions. Extensive experiments on both human and animal datasets show that our SE-ORNet can surpass state-of-the-art unsupervised point cloud shape correspondence methods.

Jiacheng Deng, Chuxin Wang, Jiahao Lu, Jianfeng He, Tianzhu Zhang, Jiyang Yu, Zhe Zhang• 2023

Related benchmarks

TaskDatasetResultRank
Non-rigid shape matchingDT4D-H
Mean Geodesic Error (x100)12.2
39
Shape MatchingSHREC19 remeshed (test)
Mean Geodesic Error4.56
37
Point cloud matchingSCAPE_r
Mean Geodesic Error18.9
23
Point cloud matchingFAUST_r
Mean Geodesic Error0.203
23
Shape CorrespondenceSurreal (test)
Accuracy21.5
16
Point cloud matchingSHREC07-H
Mean Geodesic Error12.2
14
Point cloud matchingSHREC'19_r
Mean Geodesic Error (x100)23
14
Shape CorrespondenceSHREC'20 (test)
Accuracy31.7
10
Point Cloud Shape CorrespondenceSMAL (test)
Accuracy36.4
8
3D Shape CorrespondenceSHREC Cross-dataset '19
Accuracy0.215
7
Showing 10 of 32 rows

Other info

Code

Follow for update