PointMixer: MLP-Mixer for Point Cloud Understanding
- Title
- PointMixer: MLP-Mixer for Point Cloud Understanding
- Authors
- Choe, Jaesung; Park, Chunghyun; Rameau, Francois; Park, Jaesik; Kweon, In So
- Date Issued
- 2022-10-27
- Publisher
- Springer Science and Business Media Deutschland GmbH
- 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.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/116832
- Article Type
- Conference
- Citation
- 17th European Conference on Computer Vision, ECCV 2022, page. 620 - 640, 2022-10-27
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.