Unsupervised Point Cloud Object Co-segmentation by Co-contrastive Learning and Mutual Attention Sampling
Journal
Proceedings of the IEEE International Conference on Computer Vision
Pages
7315-7324
Date Issued
2021
Author(s)
Abstract
This paper presents a new task, point cloud object co-segmentation, aiming to segment the common 3D objects in a set of point clouds. We formulate this task as an object point sampling problem, and develop two techniques, the mutual attention module and co-contrastive learning, to enable it. The proposed method employs two point samplers based on deep neural networks, the object sampler and the background sampler. The former targets at sampling points of common objects while the latter focuses on the rest. The mutual attention module explores point-wise correlation across point clouds. It is embedded in both samplers and can identify points with strong cross-cloud correlation from the rest. After extracting features for points selected by the two samplers, we optimize the networks by developing the co-contrastive loss, which minimizes feature discrepancy of the estimated object points while maximizing feature separation between the estimated object and background points. Our method works on point clouds of an arbitrary object class. It is end-to-end trainable and does not need point-level annotations. It is evaluated on the ScanObjectNN and S3DIS datasets and achieves promising results. The source code will be available at https://github.com/jimmy15923/unsup_point_coseg. © 2021 IEEE
Other Subjects
Computer vision; 3D object; Co segmentations; Extracting features; Object points; Point sampling; Point wise; Point-clouds; Sampling points; Sampling problems; Two-point; Deep neural networks
Type
conference paper