WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Visualization and Computer Graphics Year : 2022

WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration

Abstract

In this work, we present a novel method called WSDesc to learn 3D local descriptors in a weakly supervised manner for robust point cloud registration. Our work builds upon recent 3D CNN-based descriptor extractors, which leverage a voxel-based representation to parameterize local geometry of 3D points. Instead of using a predefined fixed-size local support in voxelization, we propose to learn the optimal support in a data-driven manner. To this end, we design a novel differentiable voxelization layer that can back-propagate the gradient to the support size optimization. To train the extracted descriptors, we propose a novel registration loss based on the deviation from rigidity of 3D transformations, and the loss is weakly supervised by the prior knowledge that the input point clouds have partial overlap, without requiring ground-truth alignment information. Through extensive experiments, we show that our learned descriptors yield superior performance on existing geometric registration benchmarks.

Dates and versions

hal-03831061 , version 1 (26-10-2022)

Identifiers

Cite

Lei Li, Hongbo Fu, Maks Ovsjanikov. WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration. IEEE Transactions on Visualization and Computer Graphics, 2022. ⟨hal-03831061⟩
24 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More