DeepAI AI Chat
Log In Sign Up

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

by   Zi-Ming Wang, et al.

Given two point sets, the problem of registration is to recover a transformation that matches one set to the other. This task is challenging due to the presence of the large number of outliers, the unknown non-rigid deformations and the large sizes of point sets. To obtain strong robustness against outliers, we formulate the registration problem as a partial distribution matching (PDM) problem, where the goal is to partially match the distributions represented by point sets in a metric space. To handle large point sets, we propose a scalable PDM algorithm by utilizing the efficient partial Wasserstein-1 (PW) discrepancy. Specifically, we derive the Kantorovich-Rubinstein duality for the PW discrepancy, and show its gradient can be explicitly computed. Based on these results, we propose a partial Wasserstein adversarial network (PWAN), which is able to approximate the PW discrepancy by a neural network, and minimize it by gradient descent. In addition, it also incorporates an efficient coherence regularizer for non-rigid transformations to avoid unrealistic deformations. We evaluate PWAN on practical point set registration tasks, and show that the proposed PWAN is robust, scalable and performs more favorably than the state-of-the-art methods.


page 26

page 32


Point-Set Registration: Coherent Point Drift

Point set registration is a key component in many computer vision tasks....

Robust Non-Rigid Registration With Reweighted Dual Sparsities

Non-rigid registration is challenging because it is ill-posed with high ...

Non-Rigid Point Set Registration Networks

Point set registration is defined as a process to determine the spatial ...

Fast and Robust Iterative Closet Point

The Iterative Closest Point (ICP) algorithm and its variants are a funda...

The Coherent Point Drift for Clustered Point Sets

The problem of non-rigid point set registration is a key problem for man...

On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration

This paper focuses on developing efficient and robust evaluation metrics...