REPS: Reconstruction-based Point Cloud Sampling

arXiv:2403.05047v1 Announce Type: new
Abstract: Sampling is widely used in various point cloud tasks as it can effectively reduce resource consumption. Recently, some methods have proposed utilizing neural networks to optimize the sampling process for various task requirements. Currently, deep downsampling methods can be categorized into two main types: generative-based and score-based. Generative-based methods directly generate sampled point clouds using networks, whereas score-based methods assess the importance of points according to specific rules and then select sampled point clouds based …

abstract arxiv cloud consumption cs.cv downsampling generative networks neural networks process reduce requirements sampling tasks type types