Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud

Authors

  • Mingye Xu Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences, China
  • Zhipeng Zhou Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society
  • Junhao Zhang Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Yu Qiao Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Shanghai AI Lab, Shanghai, China

Keywords:

3D Computer Vision, Segmentation, Scene Analysis & Understanding

Abstract

This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local textures but different categories, and points in isolate small hard areas, which largely harm the performance of 3D semantic segmentation. To address this challenge, we propose a novel Indistinguishable Area Focalization Network (IAF-Net), which select indistinguishable points adaptively by utilizing the hierarchical semantic features and enhance fine-grained features for points especially those indistinguishable points. We also introduce multi-stage loss to improve the feature representation in a progressive way. Moreover, in order to analyze the segmentation performances of indistinguishable areas, we propose a new evaluation metric called Indistinguishable Points Based Metric (IPBM). Our IAF-Net achieves the state-of-the-art performance on several popular 3D point datasets e.g. S3DIS and ScanNet, and clearly outperform other methods on IPBM. Our code will be available at https://github.com/MingyeXu/IAF-Net.

Downloads

Published

2021-05-18

How to Cite

Xu, M., Zhou, Z., Zhang, J., & Qiao, Y. (2021). Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3047-3055. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16413

Issue

Section

AAAI Technical Track on Computer Vision III