A deep learning framework for 3D point cloud processing is proposed in this work. In a point cloud, local neighborhoods have various shapes, and the semantic meaning of each point is determined within the local shape context. Thus, we propose shape-adaptive filters (SAFs), which are dynamically generated from the distributions of local points. The proposed SAFs can extract robust features against noise or outliers, by employing local shape contexts to suppress them. Also, we develop the SAF-Nets for classification and segmentation using multiple SAF layers. Extensive experimental results demonstrate that the proposed SAF-Nets significantly outperform the state-of-the-art conventional algorithms on several benchmark datasets. Moreover, it is shown that SAFs can improve scene flow estimation performance as well.
|Journal of Visual Communication and Image Representation
|Published - 2021 Aug
Bibliographical noteFunding Information:
This work was supported by the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (No. NRF-2018R1A2B3003896 and No. NRF-2021R1A4A1031864 ).
- Deep learning
- Point cloud processing
- Shape-adaptive filter
ASJC Scopus subject areas
- Signal Processing
- Media Technology
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering