Registration Loss Learning for Deep Probabilistic Point Set Registration

TL;DR

This paper introduces a novel end-to-end learning framework for probabilistic point set registration that incorporates learned features and a registration loss learning strategy, significantly improving recognition performance.

Contribution

It proposes a registration loss learning strategy that enables end-to-end training of probabilistic registration with learned features and attention, outperforming existing methods.

Findings

Outperforms state-of-the-art on Kitti dataset

Benefits from learned features and attention weights

Fully differentiable registration process

Abstract

Probabilistic methods for point set registration have interesting theoretical properties, such as linear complexity in the number of used points, and they easily generalize to joint registration of multiple point sets. In this work, we improve their recognition performance to match state of the art. This is done by incorporating learned features, by adding a von Mises-Fisher feature model in each mixture component, and by using learned attention weights. We learn these jointly using a registration loss learning strategy (RLL) that directly uses the registration error as a loss, by back-propagating through the registration iterations. This is possible as the probabilistic registration is fully differentiable, and the result is a learning framework that is truly end-to-end. We perform extensive experiments on the 3DMatch and Kitti datasets. The experiments demonstrate that our approach benefits significantly from the integration of the learned features and our learning strategy, outperforming the state-of-the-art on Kitti. Code is available at https://github.com/felja633/RLLReg.