WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration
This work addresses robust point cloud registration for applications like robotics or 3D scanning, but it is incremental as it builds on existing 3D CNN-based descriptor extractors.
The paper tackled the problem of learning 3D local descriptors for point cloud registration by proposing WSDesc, a weakly supervised method that optimizes support size and uses a registration loss without ground-truth alignment, resulting in superior performance on benchmarks.
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.