Neighborhood co-occurrence modeling in 3D point cloud segmentation

Computational Visual Media

Jingyu Gong¹  Lizhuang Ma²  Zhou Ye³ 

[1] Department of Computer Science and Engineering, Shanghai Jiao Tong University, 200240, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiao Tong University, 200240, Shanghai, China;MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, 200240, Shanghai, China;Shanghai CLS Fintech Co., LTD, 200030, Shanghai, China;

关键词: 3D vision;    point cloud;    co-occurrence relation modeling;    semantic segmentation;   

DOI  :  10.1007/s41095-021-0244-6

来源: Springer

【 摘 要 】

A significant performance boost has been achieved in point cloud semantic segmentation by utilization of the encoder-decoder architecture and novel convolution operations for point clouds. However, co-occurrence relationships within a local region which can directly influence segmentation results are usually ignored by current works. In this paper, we propose a neighborhood co-occurrence matrix (NCM) to model local co-occurrence relationships in a point cloud. We generate target NCM and prediction NCM from semantic labels and a prediction map respectively. Then, Kullback-Leibler (KL) divergence is used to maximize the similarity between the target and prediction NCMs to learn the co-occurrence relationship. Moreover, for large scenes where the NCMs for a sampled point cloud and the whole scene differ greatly, we introduce a reverse form of KL divergence which can better handle the difference to supervise the prediction NCMs. We integrate our method into an existing backbone and conduct comprehensive experiments on three datasets: Semantic3D for outdoor space segmentation, and S3DIS and ScanNet v2 for indoor scene segmentation. Results indicate that our method can significantly improve upon the backbone and outperform many leading competitors.

【 授权许可】

CC BY