DeepAI AI Chat
Log In Sign Up

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

by   Yue Wang, et al.

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.


page 7

page 8

page 16


Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration

While 3D-3D registration is traditionally tacked by optimization-based m...

DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration

We present DeepICP - a novel end-to-end learning-based 3D point cloud re...

Deep Confidence Guided Distance for 3D Partial Shape Registration

We present a novel non-iterative learnable method for partial-to-partial...

Maximum Likelihood Mosaics

The majority of the approaches to the automatic recovery of a panoramic ...

What Stops Learning-based 3D Registration from Working in the Real World?

Much progress has been made on the task of learning-based 3D point cloud...

PHASER: a Robust and Correspondence-free Global Pointcloud Registration

We propose PHASER, a correspondence-free global registration of sensor-c...

Keypoint Transfer for Fast Whole-Body Segmentation

We introduce an approach for image segmentation based on sparse correspo...