RAR: Region-Aware Point Cloud Registration

10/07/2021
by   Yu Hao, et al.
0

This paper concerns the research problem of point cloud registration to find the rigid transformation to optimally align the source point set with the target one. Learning robust point cloud registration models with deep neural networks has emerged as a powerful paradigm, offering promising performance in predicting the global geometric transformation for a pair of point sets. Existing methods firstly leverage an encoder to regress a latent shape embedding, which is then decoded into a shape-conditioned transformation via concatenation-based conditioning. However, different regions of a 3D shape vary in their geometric structures which makes it more sense that we have a region-conditioned transformation instead of the shape-conditioned one. In this paper we present a Region-Aware point cloud Registration, denoted as RAR, to predict transformation for pairwise point sets in the self-supervised learning fashion. More specifically, we develop a novel region-aware decoder (RAD) module that is formed with an implicit neural region representation parameterized by neural networks. The implicit neural region representation is learned with a self-supervised 3D shape reconstruction loss without the need for region labels. Consequently, the region-aware decoder (RAD) module guides the training of the region-aware transformation (RAT) module and region-aware weight (RAW) module, which predict the transforms and weights for different regions respectively. The global geometric transformation from source point set to target one is then formed by the weighted fusion of region-aware transforms. Compared to the state-of-the-art approaches, our experiments show that our RAR achieves superior registration performance over various benchmark datasets (e.g. ModelNet40).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/02/2019

Non-Rigid Point Set Registration Networks

Point set registration is defined as a process to determine the spatial ...
research
09/09/2021

Deep Hough Voting for Robust Global Registration

Point cloud registration is the task of estimating the rigid transformat...
research
01/25/2022

Self-supervised Point Cloud Registration with Deep Versatile Descriptors

Recent years have witnessed an increasing trend toward solving point clo...
research
05/22/2023

Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning

We present a new self-supervised paradigm on point cloud sequence unders...
research
07/26/2023

One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration

The precision of unsupervised point cloud registration methods is typica...
research
05/30/2022

Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors

Learning to autonomously assemble shapes is a crucial skill for many rob...
research
03/25/2018

P2P-NET: Bidirectional Point Displacement Network for Shape Transform

We introduce P2P-NET, a general-purpose deep neural network which learns...

Please sign up or login with your details

Forgot password? Click here to reset