提出轻量级LiDAR修复网络，提升恶劣天气下定位精度
ResLPR: A LiDAR Data Restoration Network and Benchmark for Robust Place Recognition Against Weather Corruptions
- 基于小波变换的网络修复受天气影响的LiDAR点云
- 在WeatherKITTI和WeatherNCLT上显著提升多种定位模型性能
- 提供首个恶劣天气下LiDAR定位基准测试集，适合自动驾驶研究
基于LiDAR的场景定位（LPR）是自动驾驶的关键组件，其对环境干扰的鲁棒性对高风险应用的安全至关重要。尽管当前最先进（SOTA）的LPR方法在晴朗天气表现良好，但在实际驾驶中常见的恶劣天气导致的点云退化问题仍难解决。为此，我们提出ResLPRNet，一种新型的LiDAR数据修复网络，通过小波变换恢复受天气影响的点云，显著提升恶劣天气下的定位性能。该网络高效轻量，可无额外计算成本地与预训练的LPR模型无缝集成。由于缺乏恶劣天气下的LPR数据集，我们构建了ResLPR基准，评估多种SOTA LPR方法在严重降雪、雾霾和降雨引起的点云失真下的表现。在新提出的WeatherKITTI和WeatherNCLT数据集上的实验表明，使用我们的修复方法可使多个LPR模型在复杂天气下取得显著性能提升。代码与数据集已开源：https://github.com/nubot-nudt/ResLPR。
原文摘要 · Abstract (English)
LiDAR-based place recognition (LPR) is a key component for autonomous driving, and its resilience to environmental corruption is critical for safety in high-stakes applications. While state-of-the-art (SOTA) LPR methods perform well in clean weather, they still struggle with weather-induced corruption commonly encountered in driving scenarios. To tackle this, we propose ResLPRNet, a novel LiDAR data restoration network that largely enhances LPR performance under adverse weather by restoring corrupted LiDAR scans using a wavelet transform-based network. ResLPRNet is efficient, lightweight and can be integrated plug-and-play with pretrained LPR models without substantial additional computational cost. Given the lack of LPR datasets under adverse weather, we introduce ResLPR, a novel benchmark that examines SOTA LPR methods under a wide range of LiDAR distortions induced by severe snow, fog, and rain conditions. Experiments on our proposed WeatherKITTI and WeatherNCLT datasets demonstrate the resilience and notable gains achieved by using our restoration method with multiple LPR approaches in challenging weather scenarios. Our code and benchmark are publicly available here: https://github.com/nubot-nudt/ResLPR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。