PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing

Hengshuang Zhao, Li Jiang, Chi-Wing Fu, Jiaya Jia; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 5565-5573

Abstract


This paper presents PointWeb, a new approach to extract contextual features from local neighborhood in a point cloud. Unlike previous work, we densely connect each point with every other in a local neighborhood, aiming to specify feature of each point based on the local region characteristics for better representing the region. A novel module, namely Adaptive Feature Adjustment (AFA) module, is presented to find the interaction between points. For each local region, an impact map carrying element-wise impact between point pairs is applied to the feature difference map. Each feature is then pulled or pushed by other features in the same region according to the adaptively learned impact indicators. The adjusted features are well encoded with region information, and thus benefit the point cloud recognition tasks, such as point cloud segmentation and classification. Experimental results show that our model outperforms the state-of-the-arts on both semantic segmentation and shape classification datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhao_2019_CVPR,
author = {Zhao, Hengshuang and Jiang, Li and Fu, Chi-Wing and Jia, Jiaya},
title = {PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}