Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

03/23/2023
by   Guofeng Mei, et al.
0

Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial overlaps. Specifically, we first adopt a network to learn posterior probability distributions of Gaussian mixture models (GMMs) from point clouds. To handle partial point cloud registration, we apply the Sinkhorn algorithm to predict the distribution-level correspondences under the constraint of the mixing weights of GMMs. To enable unsupervised learning, we design three distribution consistency-based losses: self-consistency, cross-consistency, and local contrastive. The self-consistency loss is formulated by encouraging GMMs in Euclidean and feature spaces to share identical posterior distributions. The cross-consistency loss derives from the fact that the points of two partially overlapping point clouds belonging to the same clusters share the cluster centroids. The cross-consistency loss allows the network to flexibly learn a transformation-invariant posterior distribution of two aligned point clouds. The local contrastive loss facilitates the network to extract discriminative local features. Our UDPReg achieves competitive performance on the 3DMatch/3DLoMatch and ModelNet/ModelLoNet benchmarks.

READ FULL TEXT

page 3

page 6

page 7

page 8

research
03/24/2022

A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration

3D point cloud registration in remote sensing field has been greatly adv...
research
10/17/2022

Overlap-guided Gaussian Mixture Models for Point Cloud Registration

Probabilistic 3D point cloud registration methods have shown competitive...
research
10/06/2022

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

Unsupervised learning on 3D point clouds has undergone a rapid evolution...
research
11/20/2018

Adversarial point set registration

We present a novel approach to point set registration which is based on ...
research
08/20/2020

DeepGMR: Learning Latent Gaussian Mixture Models for Registration

Point cloud registration is a fundamental problem in 3D computer vision,...
research
07/15/2021

Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds

This paper presents a novel unsupervised approach to reconstruct human s...
research
11/08/2022

DNN Filter for Bias Reduction in Distribution-to-Distribution Scan Matching

Distribution-to-distribution (D2D) point cloud registration techniques s...

Please sign up or login with your details

Forgot password? Click here to reset