BLNet:Bidirectional learning network for point clouds  

作　　者：Wenkai Han Hai Wu Chenglu Wen Cheng Wang Xin Li 

机构地区：[1]School of Informatics,Xiamen University,422 Siming South Road,Xiamen 361005,China [2]School of Electrical Engineering and Computer Science,Louisiana State University,Baton Rouge,LA 70803,USA

出　　处：《Computational Visual Media》2022年第4期585-596,共12页计算可视媒体（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant No.62171393);National Key R&D Program of China(Grant No.2021YFF0704600).

摘　　要：The key challenge in processing point clouds lies in the inherent lack of ordering and irregularity of the 3D points.By relying on per-point multi-layer perceptions(MLPs),most existing point-based approaches only address the first issue yet ignore the second one.Directly convolving kernels with irregular points will result in loss of shape information.This paper introduces a novel point-based bidirectional learning network(BLNet)to analyze irregular 3D points.BLNet optimizes the learning of 3D points through two iterative operations:feature-guided point shifting and feature learning from shifted points,so as to minimise intra-class variances,leading to a more regular distribution.On the other hand,explicitly modeling point positions leads to a new feature encoding with increased structure-awareness.Then,an attention pooling unit selectively combines important features.This bidirectional learning alternately regularizes the point cloud and learns its geometric features,with these two procedures iteratively promoting each other for more effective feature learning.Experiments show that BLNet is able to learn deep point features robustly and efficiently,and outperforms the prior state-of-the-art on multiple challenging tasks.

关 键 词：point clouds IRREGULARITY shape features bidirectional learning 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]