English

Hierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model

Computer Vision and Pattern Recognition 2022-03-16 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2202.06407,
  title  = {Hierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model},
  author = {En Yen Puang and Hao Zhang and Hongyuan Zhu and Wei Jing},
  journal= {arXiv preprint arXiv:2202.06407},
  year   = {2022}
}

Comments

Accepted by RA-Letters and ICRA 2022

R2 v1 2026-06-24T09:34:21.416Z