3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds

Aoran Xiao, Jiaxing Huang, Weihao Xuan, Ruijie Ren, Kangcheng Liu, Dayan Guan, Abdulmotaleb El Saddik, Shijian Lu, Eric P. Xing; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 9382-9392

Abstract


Robust point cloud parsing under all-weather conditions is crucial to level-5 autonomy in autonomous driving. However, how to learn a universal 3D semantic segmentation (3DSS) model is largely neglected as most existing benchmarks are dominated by point clouds captured under normal weather. We introduce SemanticSTF, an adverse-weather point cloud dataset that provides dense point-level annotations and allows to study 3DSS under various adverse weather conditions. We investigate universal 3DSS modeling with two tasks: 1) domain adaptive 3DSS that adapts from normal-weather data to adverse-weather data; 2) domain generalized 3DSS that learns a generalizable model from normal-weather data. Our studies reveal the challenge while existing 3DSS methods encounter adverse-weather data, showing the great value of SemanticSTF in steering the future endeavor along this very meaningful research direction. In addition, we design a domain randomization technique that alternatively randomizes the geometry styles of point clouds and aggregates their encoded embeddings, ultimately leading to a generalizable model that effectively improves 3DSS under various adverse weather. The SemanticSTF and related codes are available at https://github.com/xiaoaoran/SemanticSTF.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Aoran and Huang, Jiaxing and Xuan, Weihao and Ren, Ruijie and Liu, Kangcheng and Guan, Dayan and El Saddik, Abdulmotaleb and Lu, Shijian and Xing, Eric P.}, title = {3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9382-9392} }