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

Authors: Sunghwan Yoo, Yeongjeong Jeong, Maryam Jameela, Gunho Sohn

Department of Earth and Space Science and Engineering, York University Toronto, ON M3J 1P3 Canada

CVPR PCV Workshop 2023

Abstract

We proposed 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.

Overview

SensatUrban Results

Toronto3D Results

Main Contributors: Jacob Yoo

Publications:

• Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenes, CVPR PCV Workshop, 2023