Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classification. (arXiv:2210.15514v1 [cs.CV])

Great progress has been made in point cloud classification with
learning-based methods. However, complex scene and sensor inaccuracy in
real-world application make point cloud data suffer from corruptions, such as
occlusion, noise and outliers. In this work, we propose Point-Voxel based
Adaptive (PV-Ada) feature abstraction for robust point cloud classification
under various corruptions. Specifically, the proposed framework iteratively
voxelize the point cloud and extract point-voxel feature with shared local
encoding and Transformer. Then, adaptive max-pooling is proposed to robustly
aggregate …

arxiv classification cloud feature voxel