Adaptive Channel Encoding Transformer for Point Cloud Analysis

TL;DR

This paper introduces an adaptive channel encoding transformer for point cloud analysis that captures relationships between features and coordinates, improving classification and segmentation performance.

Contribution

It proposes a novel Transformer-Conv for adaptive channel encoding and uses dual semantic receptive fields to enhance point cloud analysis.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effective in point cloud classification and segmentation

Demonstrates superior encoding of feature channels

Abstract

Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis. Since they mainly focus on point-wise transformer, an adaptive channel encoding transformer is proposed in this paper. Specifically, a channel convolution called Transformer-Conv is designed to encode the channel. It can encode feature channels by capturing the potential relationship between coordinates and features. Compared with simply assigning attention weight to each channel, our method aims to encode the channel adaptively. In addition, our network adopts the neighborhood search method of low-level and high-level dual semantic receptive fields to improve the performance. Extensive experiments show that our method is superior to state-of-the-art point cloud classification and segmentation methods on three benchmark datasets.