Abstract
Point cloud processing is a highly challenging task in 3D vision because it is unstructured and unordered. Recently, deep learning has been proven to be quite successful in point cloud recognition, registration, segmentation, etc. Neighborhood search operation is an important component of point cloud deep learning models, and directly affects the performance of the model. In this paper, we propose a learnable neighborhood search method. This method adaptively chooses an appropriate search method based on the characteristics of each point, thus avoiding the disadvantage of selecting the search method manually. We validate the proposed methods on ModelNet40 dataset and ShapeNetPart dataset, and all the chosen models achieved a performance improvement with a maximum improvement of 1.1%. The proposed method is a plug-and-play technique and can be easily integrated into existing methods.
Funding Information
  • National Natural Science Foundation of China (11673079, 11673079, 11673079)
  • National Key Research and Development Program of China (2018YFB0505105, 2018YFB0505105)

This publication has 14 references indexed in Scilit: