awesome-point-cloud-transformers

Papers

3D

[Arxiv] Dual Transformer for Point Cloud Analysis.

[Arxiv] Centroid Transformers: Learning to Abstract with Attention.

[Arxiv] CvT: Introducing Convolutions to Vision Transformers. [Code] [Pytorch]

[Arxiv] Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks.

[Arxiv] Iterative SE(3)-Transformers.

[Arxiv] Iterative Transformer Network for 3D Point Cloud. [Code]

[CVM] PCT: Point Cloud Transformer. [Code]

[Arxiv] Point Cloud Learning with Transformer.

[Arxiv] Point Transformer.

[Arxiv] Point Transformer.

[NeurIPS] SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks. [Code]

[TPAMI] [Arxiv] Spatial Transformer for 3D Point Clouds. [Code]

[ICCV] SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer. [Code]

[Arxiv] Point-Voxel Transformer: An Efficient Approach To 3D Deep Learning. [Code coming soon]

[IJCAI] Local Representation is Not Enough: Soft Point-wise Transformer for Descriptor and Detector of Local Features.

[RGate] PCTMA-Net: Point Cloud Transformer with Morphing Atlas-based Point Generation Network for Dense Point Cloud Completion.

[Arxiv] SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition.

[Arxiv] NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation. [Code]

[MLSciTech] Point cloud transformers applied to collider physics.

[Arxiv] Point Transformer for Shape Classification and Retrieval of 3D and Urban Roof Point Clouds.

[ICMLW] Generative Adversarial Set Transformers.

[Arxiv] TransSC: Transformer-based Shape Completion for Grasp Evaluation.

[Arxiv] TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding.

[Arxiv] Improving 3D Object Detection with Channel-wise Transformer.

[MDPI] Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar.

[Arxiv] PatchFormer: A Versatile 3D Transformer Based on Patch Attention.

[Arxiv] PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds.[Code]

[Arxiv]An End-to-End Transformer Model for 3D Object Detection.[Project Page]

[IROS]PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds.[Code coming Soon]

4D

[CVPR] Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos. [CODE]

[ICLR] PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences. [Code]

[TIM] Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences.

[Arxiv] Spatial-Temporal Transformer for 3D Point Cloud Sequences.

[Arxiv] SequentialPointNet: A strong parallelized point cloud sequence classification network for 3D action recognition [Code]

[Arxiv] GeometryMotion-Net: A Strong Two-stream Baseline for 3D Action Recognition.