PointCAT: Cross-Attention Transformer for point cloud

by   Xincheng Yang, et al.
Nanjing University

Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning are still in their infancy compared to other methods. In this paper we present Point Cross-Attention Transformer (PointCAT), a novel end-to-end network architecture using cross-attentions mechanism for point cloud representing. Our approach combines multi-scale features via two seprate cross-attention transformer branches. To reduce the computational increase brought by multi-branch structure, we further introduce an efficient model for shape classification, which only process single class token of one branch as a query to calculate attention map with the other. Extensive experiments demonstrate that our method outperforms or achieves comparable performance to several approaches in shape classification, part segmentation and semantic segmentation tasks.


Dual Transformer for Point Cloud Analysis

Following the tremendous success of transformer in natural language proc...

Point Cloud Learning with Transformer

Remarkable performance from Transformer networks in Natural Language Pro...

PointMixer: MLP-Mixer for Point Cloud Understanding

MLP-Mixer has newly appeared as a new challenger against the realm of CN...

Point Cloud Recognition with Position-to-Structure Attention Transformers

In this paper, we present Position-to-Structure Attention Transformers (...

ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understanding

Recently, a growing number of work design unsupervised paradigms for poi...

Adaptive Channel Encoding Transformer for Point Cloud Analysis

Transformer plays an increasingly important role in various computer vis...

LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling

Compared with traditional task-irrelevant downsampling methods, task-ori...

Please sign up or login with your details

Forgot password? Click here to reset