PCT: Point cloud transformer
Explore this paper's citation graph
Summary
A novel framework based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing, is presented, which is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
- Type
- article
- Published
- 2020-12-17
- Cited by
- 2,249
- References
- 50
- Access
- Open access
- OpenAlex
- https://openalex.org/W3111535274
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:229297794
Keywords
Point cloud, Embedding, Transformer, Cloud computing, Computer graphics
References
- Spectral Networks and Locally Connected Networks on Graphs
- A scalable active framework for region annotation in 3D shape collections
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
- Residual Attention Network for Image Classification
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Squeeze-and-Excitation Networks
- SEGCloud: Semantic Segmentation of 3D Point Clouds
- Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs
- SO-Net: Self-Organizing Network for Point Cloud Analysis
- Point convolutional neural networks by extension operators
- Tangent Convolutions for Dense Prediction in 3D
- Attentional ShapeContextNet for Point Cloud Recognition
- PointGrid: A Deep Network for 3D Shape Understanding
- Monte Carlo convolution for learning on non-uniformly sampled point clouds
- PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames
- PointCNN: Convolution On X-Transformed Points
- Transformer-XL: Attentive Language Models beyond a Fixed-Length Context
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- KPConv: Flexible and Deformable Convolution for Point Clouds
Cited by
- Parameter-Efficient Person Re-Identification in the 3D Space
- Multiscale Mesh Deformation Component Analysis With Attention-Based Autoencoders
- PointCutMix: Regularization Strategy for Point Cloud Classification
- Transformers in Vision: A Survey
- Point cloud transformers applied to collider physics
- Towards Efficient Graph Convolutional Networks for Point Cloud Handling
- PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
- Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
- M3DETR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
- LinkNet: 2D-3D linked multi-modal network for online semantic segmentation of RGB-D videos
- Dual Transformer for Point Cloud Analysis
- Can attention enable MLPs to catch up with CNNs?
- SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
- Subdivision-based Mesh Convolution Networks
- Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar
- Improving Object Grasp Performance via Transformer-Based Sparse Shape Completion
- Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection
- Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
- A Survey on Vision Transformer
- SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer
Related papers
- Deep learning for image segmentation-a short survey
- Performance evaluation of 2D and 3D deep learning approaches for automatic segmentation of multiple organs on CT images
- Automated pancreas segmentation and volumetry using deep neural network on computed tomography
- Automated Pancreas Segmentation And Volumetry Using Deep Neural Network On Computed Tomography
- Understanding Deep Learning Techniques for Image Segmentation
- A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification
- MOG: a background extraction approach for data augmentation of time-series images in deep learning segmentation