3CROSSNet: Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation
- 1 February 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 3718-3725
Abstract
Self-attention mechanism recently achieves impressive advancement in Natural Language Processing (NLP) and Image Processing domains. Its permutation invariance property makes it ideally suitable for point cloud processing. Inspired by this remarkable success, we propose an end-to-end architecture, dubbed Cross-Level Cross-Scale Cross-Attention Network (3CROSSNet), for point cloud representation learning. First, a point-wise feature pyramid module is introduced to hierarchically extract features from different scales or resolutions. Then a cross-level cross-attention module is designed to model long-range inter-level and intra-level dependencies. Finally, we develop a cross-scale cross-attention module to capture interactions between-and-within scales for representation enhancement. Compared with state-of-the-art approaches, our network can obtain competitive performance on challenging 3D object classification, point cloud segmentation tasks via comprehensive experimental evaluation. The source code and trained models are available at. 1Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62002299)
- Natural Science Foundation of Chongqing, China (cstc2020jcyj-msxmX0126)
- Fundamental Research Funds for the Central Universities (SWU120005)
This publication has 49 references indexed in Scilit:
- Point convolutional neural networks by extension operatorsACM Transactions on Graphics, 2018
- 3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural NetworksIEEE Robotics and Automation Letters, 2018
- Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models2017
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs2017
- OctNet: Learning Deep 3D Representations at High Resolutions2017
- A scalable active framework for region annotation in 3D shape collectionsACM Transactions on Graphics, 2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- 3D ShapeNets: A deep representation for volumetric shapes2015
- NOVELNEURALMODULATORSAnnual Review of Neuroscience, 2003