Searching Dense Point Correspondences via Permutation Matrix Learning

by   Zhiyuan Zhang, et al.

Although 3D point cloud data has received widespread attentions as a general form of 3D signal expression, applying point clouds to the task of dense correspondence estimation between 3D shapes has not been investigated widely. Furthermore, even in the few existing 3D point cloud-based methods, an important and widely acknowledged principle, i.e . one-to-one matching, is usually ignored. In response, this paper presents a novel end-to-end learning-based method to estimate the dense correspondence of 3D point clouds, in which the problem of point matching is formulated as a zero-one assignment problem to achieve a permutation matching matrix to implement the one-to-one principle fundamentally. Note that the classical solutions of this assignment problem are always non-differentiable, which is fatal for deep learning frameworks. Thus we design a special matching module, which solves a doubly stochastic matrix at first and then projects this obtained approximate solution to the desired permutation matrix. Moreover, to guarantee end-to-end learning and the accuracy of the calculated loss, we calculate the loss from the learned permutation matrix but propagate the gradient to the doubly stochastic matrix directly which bypasses the permutation matrix during the backward propagation. Our method can be applied to both non-rigid and rigid 3D point cloud data and extensive experiments show that our method achieves state-of-the-art performance for dense correspondence learning.


page 1

page 4


End-to-end Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration

Even though considerable progress has been made in deep learning-based 3...

CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

This paper addresses the problem of computing dense correspondence betwe...

Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences

Correspondence search is an essential step in rigid point cloud registra...

DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction

We present a new method for real-time non-rigid dense correspondence bet...

Correspondence Learning via Linearly-invariant Embedding

In this paper, we propose a fully differentiable pipeline for estimating...

RoCNet: 3D Robust Registration of Point-Clouds using Deep Learning

This paper introduces a new method for 3D point cloud registration based...

MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling

Downsampling is a commonly-used technique in 3D point cloudprocessing fo...

Please sign up or login with your details

Forgot password? Click here to reset