Learning Inner-Group Relations on Point Clouds
Authors:
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15457-15467
Abstract
The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The module computes a feature of a group based on the aggregation of the features of the inner-group points weighted by geometric relations and semantic relations. We adopt this module to design our RPNet. We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation. Surprisingly, empirical results show that wider RPNet fits for classification, while deeper RPNet works better on segmentation. RPNet achieves state-of-the-art for classification and segmentation on challenging benchmarks. We also compare our local aggregator with PointNet++, with around 30% parameters and 50% computation saving. Finally, we conduct experiments to reveal the robustness of RPNet with regard to rigid transformation and noises.Keywords
All Related Versions
This publication has 45 references indexed in Scilit:
- Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models2017
- O-CNNACM Transactions on Graphics, 2017
- Residual Attention Network for Image Classification2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- OctNet: Learning Deep 3D Representations at High Resolutions2017
- Multi-View 3D Object Retrieval With Deep Embedding NetworkIEEE Transactions on Image Processing, 2016
- DeepShape: Deep-Learned Shape Descriptor for 3D Shape RetrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015