Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene
This work addresses the challenge of handling dense point clouds in outdoor scenes for applications like autonomous driving or robotics, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of semantic segmentation for large-scale outdoor point clouds by proposing EyeNet, which introduces a multi-contour input and parallel processing network inspired by human peripheral vision, achieving state-of-the-art performance on relevant datasets.
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.