EEP-Net: Enhancing Local Neighborhood Features and Efficient Semantic Segmentation of Scale Point Clouds

Yicheng Liu, Fuxiang Wu, Qieshi Zhang, Ziliang Ren, Jun Cheng

Abstract: Semantic segmentation of point clouds at the scene level is a challenging task. Most existing work relies on expensive sampling techniques and tedious pre- and post-processing steps, which are often time-consuming and laborious. To solve this problem, we propose a new module for extracting contextual features from local regions of point clouds, called EEP module in this paper, which converts point clouds from Cartesian coordinates to polar coordinates of local regions, thereby Fade out the geometric representation with rotation invariance in the three directions of XYZ, and the new geometric representation is connected with the position code to form a new spatial representation. It can preserve geometric details and learn local features to a greater extent while improving computational and storage efficiency. This is beneficial for the segmentation task of point clouds. To validate the performance of our method, we conducted experiments on the publicly available standard dataset S3DIS, and the experimental results show that our method achieves competitive results compared to existing methods.