RotInv-PCT: Rotation-Invariant Point Cloud Transformer via feature separation and aggregation
- 4 February 2025
- journal article
- Published by Elsevier in Neural Networks
- Vol. 185, 107223
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62293513)
- National Natural Science Foundation of China (62106109)
- Tianjin Municipal Natural Science Foundation (22JCZDJC00810)
This publication has 44 references indexed in Scilit:
- Unsupervised distribution-aware keypoints generation from 3D point cloudsNeural Networks, 2024
- MSDCNN: A multiscale dilated convolution neural network for fine-grained 3D shape classificationNeural Networks, 2024
- Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approachNeural Networks, 2023
- Rotation invariant point cloud analysis: Where local geometry meets global topologyPattern Recognition, 2022
- PCT: Point cloud transformerComputational Visual Media, 2021
- 3D-Rotation-Equivariant Quaternion Neural Networks2020
- Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis2020
- Rotation Invariant Convolutions for 3D Point Clouds Deep Learning2019
- PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors2018
- Learning SO(3) Equivariant Representations with Spherical CNNs2018