AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Point Cloud Analysis

arXiv:2402.17521v1 Announce Type: new
Abstract: Efficient downsampling plays a crucial role in point cloud learning, particularly for large-scale 3D scenes. Existing downsampling methods either require a huge computational burden or sacrifice fine-grained geometric information. This paper presents an advanced sampler that achieves both high accuracy and efficiency. The proposed method utilizes voxel-based sampling as a foundation, but effectively addresses the challenges regarding voxel size determination and the preservation of critical geometric cues. Specifically, we propose a Voxel Adaptation Module that …

analysis arxiv cloud cs.cv sampling type voxel