Publications

Detailed Information

PointMixer: MLP-Mixer for Point Cloud Understanding

Cited 15 time in Web of Science Cited 19 time in Scopus
Authors

Choe, Jaesung; Park, Chunghyun; Rameau, Francois; Park, Jaesik; Kweon, In So

Issue Date
2022
Publisher
Springer Verlag
Citation
Lecture Notes in Computer Science, Vol.13687, pp.620-640
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 image recognition tasks. Unlike images, point clouds are inherently sparse, unordered and irregular, which limits the direct use of MLP-Mixer for point cloud understanding. To overcome these limitations, we propose PointMixer, a universal point set operator that facilitates information sharing among unstructured 3D point cloud. By simply replacing token-mixing MLPs with Softmax function, PointMixer can mix features within/between point sets. By doing so, PointMixer can be broadly used for intra-set, inter-set, and hierarchical-set mixing. We demonstrate that various channel-wise feature aggregation in numerous point sets is better than self-attention layers or dense token-wise interaction in a view of parameter efficiency and accuracy. Extensive experiments show the competitive or superior performance of PointMixer in semantic segmentation, classification, and reconstruction against Transformer-based methods.
ISSN
0302-9743
URI
https://hdl.handle.net/10371/201290
DOI
https://doi.org/10.1007/978-3-031-19812-0_36
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • College of Engineering
  • Dept. of Computer Science and Engineering
Research Area Computer Graphics, Computer Vision, Machine Learning, Robotics

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share