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

Sunghwan Yoo, Yeonjeong Jeong, Maryam Jameela, Gunho Sohn; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 6577-6586

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-contour 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.

Related Material

[pdf] [arXiv]
[bibtex]
@InProceedings{Yoo_2023_CVPR, author = {Yoo, Sunghwan and Jeong, Yeonjeong and Jameela, Maryam and Sohn, Gunho}, title = {Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {6577-6586} }