Registration Loss Learning for Deep Probabilistic Point Set Registration

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.

arXiv comment3DV 2020

References in corpus (6)

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Point-Set Registration: Coherent Point Drift
• Open3D: A Modern Library for 3D Data Processing
• 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
• PRNet: Self-Supervised Learning for Partial-to-Partial Registration
• 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions