Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenes

Sunghwan Yoo, Yeonjeong Jeong, Maryam Jameela, Gunho Sohn

CVPRW 2023 pp. 6577-6586

doi:10.1109/CVPRW59228.2023.00699 /cvprw/2023/yoo2023cvprw-human/

Abstract

This paper proposes EyeNet, a novel semantic segmentation network for point clouds that addresses the critical yet often overlooked parameter of coverage area size. Inspired by human peripheral vision, EyeNet overcomes the limitations of conventional networks by introducing a simple but efficient multi-scale input and a parallel processing network with connection blocks between parallel streams. The proposed approach effectively addresses the challenges of dense point clouds, as demonstrated by our ablation studies and state-of-the-art performance on Large-Scale Outdoor datasets.

CVPRW Semantic Scholar

Cite

Text

Yoo et al. "Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00699

Markdown

[Yoo et al. "Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/yoo2023cvprw-human/) doi:10.1109/CVPRW59228.2023.00699

BibTeX

@inproceedings{yoo2023cvprw-human,
  title     = {{Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenes}},
  author    = {Yoo, Sunghwan and Jeong, Yeonjeong and Jameela, Maryam and Sohn, Gunho},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {6577-6586},
  doi       = {10.1109/CVPRW59228.2023.00699},
  url       = {https://mlanthology.org/cvprw/2023/yoo2023cvprw-human/}
}