Correspondence Matrices are Underrated - Robotics Institute Carnegie Mellon University

Correspondence Matrices are Underrated

Tejas Zodage, Rahul Chakwate, Vinit Sarode, Rangaprasad Arun Srivatsan, and Howie Choset
Conference Paper, Proceedings of International Conference on 3D Vision (3DV '20), pp. 603 - 612, November, 2020

Abstract

Point-cloud registration (PCR) is an important task in various applications such as robotic manipulation, augmented and virtual reality, SLAM, etc. PCR is an optimization problem involving minimization over two different types of interdependent variables: transformation parameters and point-to-point correspondences. Recent developments in deep-learning have produced computationally fast approaches for PCR. The loss functions that are optimized in these networks are based on the error in the transformation parameters. We hypothesize that these methods would perform significantly better if they calculated their loss function using correspondence error instead of only using error in transformation parameters. We define correspondence error as a metric based on incorrectly matched point pairs. We provide a fundamental explanation for why this is the case and test our hypothesis by modifying existing methods to use correspondence-based loss instead of transformation-based loss. These experiments show that the modified networks converge faster and register more accurately even at larger misalignment when compared to the original networks.

BibTeX

@conference{Zodage-2020-126892,
author = {Tejas Zodage and Rahul Chakwate and Vinit Sarode and Rangaprasad Arun Srivatsan and Howie Choset},
title = {Correspondence Matrices are Underrated},
booktitle = {Proceedings of International Conference on 3D Vision (3DV '20)},
year = {2020},
month = {November},
pages = {603 - 612},
}