Task-Aware Sampling Layer for Point-Wise Analysis
Open Access
- 3 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 30 (10) , 6612-6624
Abstract
Sampling, grouping, and aggregation are three important components in the multi-scale analysis of point clouds. In this paper, we present a novel data-driven sampler learning strategy for point-wise analysis tasks. Unlike the widely used sampling technique, Farthest Point Sampling (FPS), we propose to learn sampling and downstream applications jointly. Our key insight is that uniform sampling methods like FPS are not always optimal for different tasks: sampling more points around boundary areas can make the point-wise classification easier for segmentation. Towards this end, we propose a novel sampler learning strategy that learns sampling point displacement supervised by task-related ground truth information and can be trained jointly with the underlying tasks. We further demonstrate our methods in various point-wise analysis tasks, including semantic part segmentation, point cloud completion, and keypoint detection. Our experiments show that jointly learning of the sampler and task brings better performance than using FPS in various point-based networks.Keywords
All Related Versions
Funding Information
- Key Area R&D Program of Guangdong Province (2018B030338001)
- National Key R&D Program of China (2018YFB1800800)
- Shenzhen Outstanding Talents Training Fund
- Guangdong Research Project (2017ZT07X152)
This publication has 48 references indexed in Scilit:
- Flex-Convolution2019
- SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters2018
- Local Spectral Graph Convolution for Point Set Feature Learning2018
- PCN: Point Completion Network2018
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Volumetric and Multi-view CNNs for Object Classification on 3D Data2016
- Deep Residual Learning for Image Recognition2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- 3D ShapeNets: A deep representation for volumetric shapes2015
- The farthest point strategy for progressive image samplingIEEE Transactions on Image Processing, 1997