重新思考恶劣天气下鲁棒LiDAR语义分割的数据增强
Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather
AI总结：
针对恶劣天气下LiDAR语义分割性能下降问题，提出基于几何扰动和点丢失两种关键因素的选择性抖动与可学习点丢弃数据增强方法，在基准上提升8.1个百分点，达到新最先进水平。
摘要：
现有的LiDAR语义分割方法在恶劣天气条件下常常面临性能下降的问题。以往的工作通过模拟恶劣天气或在训练期间采用通用数据增强来解决这一问题。然而，这些方法缺乏对恶劣天气如何负面影响LiDAR语义分割性能的详细分析和理解。受此问题驱动，我们识别了恶劣天气的关键因素，并进行了玩具实验以确定性能下降的主要原因：（1）由空气中雾或水滴引起的折射导致的几何扰动，以及（2）由能量吸收和遮挡引起的点云丢失。基于这些发现，我们提出了新的战略性数据增强技术。首先，我们引入了选择性抖动（SJ），在随机的深度（或角度）范围内抖动点，以模拟几何扰动。此外，我们开发了可学习点丢弃（LPD），利用深度Q学习网络学习易受攻击的擦除模式，以近似恶劣天气条件下的点云丢失现象。无需精确的天气模拟，这些技术通过将模型暴露于我们以数据为中心的分析所识别的易受攻击条件，增强了LiDAR语义分割模型的鲁棒性。实验结果证实了所提出的数据增强方法在增强对恶劣天气条件鲁棒性方面的适用性。我们的方法在SemanticKITTI-to-SemanticSTF基准上达到了显著的39.5 mIoU，将基线提高了8.1个百分点，并建立了新的最先进水平。我们的代码将在\url{https://github.com/engineerJPark/LiDARWeather}发布。
英文摘要：
Existing LiDAR semantic segmentation methods often struggle with performance declines in adverse weather conditions. Previous work has addressed this issue by simulating adverse weather or employing universal data augmentation during training. However, these methods lack a detailed analysis and understanding of how adverse weather negatively affects LiDAR semantic segmentation performance. Motivated by this issue, we identified key factors of adverse weather and conducted a toy experiment to pinpoint the main causes of performance degradation: (1) Geometric perturbation due to refraction caused by fog or droplets in the air and (2) Point drop due to energy absorption and occlusions. Based on these findings, we propose new strategic data augmentation techniques. First, we introduced a Selective Jittering (SJ) that jitters points in the random range of depth (or angle) to mimic geometric perturbation. Additionally, we developed a Learnable Point Drop (LPD) to learn vulnerable erase patterns with a Deep Q-Learning Network to approximate the point drop phenomenon from adverse weather conditions. Without precise weather simulation, these techniques strengthen the LiDAR semantic segmentation model by exposing it to vulnerable conditions identified by our data-centric analysis. Experimental results confirmed the suitability of the proposed data augmentation methods for enhancing robustness against adverse weather conditions. Our method achieves a notable 39.5 mIoU on the SemanticKITTI-to-SemanticSTF benchmark, improving the baseline by 8.1\%p and establishing a new state-of-the-art. Our code will be released at \url{https://github.com/engineerJPark/LiDARWeather}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
