Hierarchical Point Cloud Encoding and Decoding With Lightweight Self-Attention Based Model

Hierarchical Point Cloud Encoding and Decoding With Lightweight Self-Attention Based Model

IEEE Robotics and Automation Letters

10.1109/LRA.2022.3149569

http://dx.doi.org/10.1109/lra.2022.3149569

En Yen Puang, Hao Zhang, Hongyuan Zhu, Wei Jing

Mechanical Engineering, Computer Science Applications, Control and Systems Engineering, Human-Computer Interaction, Computer Vision and Pattern Recognition, Control and Optimization, artificial intelligence, Biomedical engineering

08 February 2022

Puang, E. Y., Zhang, H., Zhu, H., & Jing, W. (2022). Hierarchical Point Cloud Encoding and Decoding With Lightweight Self-Attention Based Model. IEEE Robotics and Automation Letters, 7(2), 4542–4549. https://doi.org/10.1109/lra.2022.3149569

In this paper we present SA-CNN, a hierarchical and lightweight self-attention based encoding and decoding architecture for representation learning of point cloud data. The proposed SA-CNN introduces convolution and transposed convolution stacks to capture and generate contextual information among unordered 3D points. Following conventional hierarchical pipeline, the encoding process extracts feature in local-to-global manner, while the decoding process generates feature and point cloud in coarse-to-fine, multi-resolution stages. We demonstrate that SA-CNN is capable of a wide range of applications, namely classification, part segmentation, reconstruction, shape retrieval, and unsupervised classification. While achieving the state-of-the-art or comparable performance in the benchmarks, SA-CNN maintains its model complexity several order of magnitude lower than the others. In term of qualitative results, we visualize the multi-stage point cloud reconstructions and latent walks on rigid objects as well as deformable non-rigid human and robot models.

Publisher Copyright

This research / project is supported by the A*STAR - AME Programmatic Funding Scheme
Grant Reference no. : A18A2b0046

This research / project is supported by the A*STAR - Career Development Fund
Grant Reference no. : C210812033

This research / project is supported by the A*STAR - RobotHTPO Seed Fund
Grant Reference no. : C211518008

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/16573

2377-3766
2377-3774

Institute for Infocomm Research