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

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

About

We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning-based methods for registration, we use deep networks to tackle non-convexity of the alignment and partial correspondence problems. While previous learning-based methods assume the entire shape is visible, PRNet is suitable for partial-to-partial registration, outperforming PointNetLK, DCP, and non-learning methods on synthetic data. PRNet is self-supervised, jointly learning an appropriate geometric representation, a keypoint detector that finds points in common between partial views, and keypoint-to-keypoint correspondences. We show PRNet predicts keypoints and correspondences consistently across views and objects. Furthermore, the learned representation is transferable to classification.

Yue Wang, Justin M. Solomon• 2019

Related benchmarks

TaskDatasetResultRank
Point cloud registrationModelNet40 (Unseen categories)
RMSE (Rotation)3.199
36
Point cloud registrationModelNet40 RPMNet manner (Unseen Shapes)
RMSE(R)1.588
32
Point cloud registrationModelNet40 twice-sampled (TS) unseen categories (test)
RMSE (Rotation)2.712
30
Point cloud registrationModelNet40 Unseen Categories with Gaussian Noise RPMNet manner (OS)
RMSE (Rotation)1.911
21
Point cloud registrationModelNet40 PRNet generation manner with Gaussian noise (unseen categories)
RMSE (Rotation)3.241
20
Point cloud registrationModelNet40 Gaussian Noise twice-sampled (test)
RMSE (R)3.197
11
Rigid Point Cloud RegistrationModelNet40 unseen objects + Gaussian noise
RMSE (R)4.32
7
Point cloud registrationModelNet40 8 axisymmetrical categories PRNet/RPMNet generation (once-sampled (OS))
RMSE (Rotation)5.979
4
Point cloud registrationModelNet40 8 axisymmetrical categories PRNet/RPMNet generation (twice-sampled (TS))
RMSE (R)13.773
4
Showing 9 of 9 rows

Other info

Follow for update