ResLPR

Given the lack of LiDAR-based place recognition (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. Specifically, we constructed the WeatherKITTI and WeatherNCLT datasets based on the widely used LPR datasets KITTI and NCLT, utilizing the simulation methods based on physical principles and engineering experience.针对恶劣天气下基于激光雷达的场景识别（LiDAR-based place recognition, LPR）数据集缺失的问题，我们提出了全新基准测试集ResLPR，用于在强降雪、大雾及强降雨等恶劣天气诱发的各类激光雷达畸变场景中，检验当前最优（state-of-the-art, SOTA）LPR方法的性能。 具体而言，我们基于目前广泛应用的LPR数据集KITTI与NCLT，结合基于物理原理与工程经验的仿真方法，构建了WeatherKITTI与WeatherNCLT两款数据集。