PointMixer: MLP-Mixer for Point Cloud Understanding

Abstract

MLP-Mixer has newly appeared as a new challenger against the realm of CNNs and transformer. Despite its simplicity compared to transformer, the concept of channel-mixing MLPs and token-mixing MLPs achieves noticeable performance in visual recognition tasks. Unlike images, point clouds are inherently sparse, unordered and irregular, which limits the direct use of MLP-Mixer for point cloud understanding. In this paper, we propose PointMixer, a universal point set operator that facilitates information sharing among unstructured 3D points. By simply replacing token-mixing MLPs with a softmax function, PointMixer can "mix" features within/between point sets. By doing so, PointMixer can be broadly used in the network as inter-set mixing, intra-set mixing, and pyramid mixing. Extensive experiments show the competitive or superior performance of PointMixer in semantic segmentation, classification, and point reconstruction against transformer-based methods.

Accepted to ECCV 2022

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• MLP-Mixer: An all-MLP Architecture for Vision
• Open3D: A Modern Library for 3D Data Processing
• Transformer in Transformer
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Submanifold Sparse Convolutional Networks
• CycleMLP: A MLP-like Architecture for Dense Prediction
• AS-MLP: An Axial Shifted MLP Architecture for Vision
• LambdaNetworks: Modeling Long-Range Interactions Without Attention
• S${}^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision
• S${}^2$-MLP: Spatial-Shift MLP Architecture for Vision
• Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition
• ConvMLP: Hierarchical Convolutional MLPs for Vision
• Deep Point Cloud Reconstruction
• Hire-MLP: Vision MLP via Hierarchical Rearrangement