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

TL;DR

This paper introduces SemanticSTF, a new adverse-weather point cloud dataset, and proposes a domain randomization technique to improve 3D semantic segmentation models' robustness across different weather conditions.

Contribution

It provides the first comprehensive study of 3D semantic segmentation under adverse weather and develops a novel domain randomization method for better generalization.

Findings

Existing methods struggle with adverse-weather data.

SemanticSTF enables effective training and evaluation in adverse conditions.

The proposed domain randomization improves model robustness across weather scenarios.

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 study all-weather 3DSS modeling under two setups: 1) domain adaptive 3DSS that adapts from normal-weather data to adverse-weather data; 2) domain generalizable 3DSS that learns all-weather 3DSS models 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 embeddings, ultimately leading to a generalizable model that can improve 3DSS under various adverse weather effectively. The SemanticSTF and related codes are available at \url{https://github.com/xiaoaoran/SemanticSTF}.