State-of-the-art object detection systems for autonomous driving achieve promising results in clear weather conditions. However, such autonomous safety critical systems also need to work in degrading weather conditions, such as rain, fog and snow. Unfortunately, most approaches evaluate only on the KITTI dataset, which consists only of clear weather scenes. In this paper we address this issue and perform one of the most detailed evaluation on single and dual modality architectures on data captured in real weather conditions. We analyse the performance degradation of these architectures in degrading weather conditions. We demonstrate that an object detection architecture performing good in clear weather might not be able to handle degrading weather conditions. We also perform ablation studies on the dual modality architectures and show their limitations.
WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention
School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology（浙江理工大学人工智能与信息工程学院）；Department of Computer and Information Sciences, Northumbria University（北爱尔兰北umbria大学计算机与信息科学系）；Beijing Quinovare Medical Technology Co., Ltd（北京启诺医疗科技有限公司）；School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）
Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；Institute of Information Engineering, CAS（中国科学院信息工程研究所）
Object detection in adverse weather conditions for autonomous vehicles using Instruct Pix2Pix
High-Performance Embedded Systems (HPES) Lab（高性能嵌入式系统实验室）；Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Computer Science Dept.（计算机科学系）；Univ. Politècnica de Catalunya（巴塞罗那理工大学）；IDEAI-UPC- Research Center（IDEAI-UPC研究中心）
Robustness Evaluation and Adversarial Training of an Instance Segmentation Model
General Motors Company（通用汽车公司）
为了评估非分类器模型的鲁棒性，我们提出了概率局部等价，基于随机平滑的概念，作为一种定量评估任意函数的鲁棒性的方法。此外，为了了解对抗训练对非分类器的影响，并研究在不降低训练分布性能的情况下可以获得的鲁棒性水平，我们将Fast is Better than Free对抗训练与TRADES鲁棒损失一起应用于实例分割网络的训练。在这个方向上，我们能够在TuSimple车道检测挑战中实现0.85的对称最佳骰子得分，优于标准训练网络的0.82得分。此外，我们能够在操作输入上获得0.49的F测量值，而标准训练网络的分数为0。我们证明了概率局部等价能够成功区分标准训练模型和逆向训练模型，提供了逆向训练模型鲁棒性提高的另一种观点。
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
ETH Zürich（苏黎世联邦理工学院）；MPI for Informatics（马克斯·普朗克信息学研究所）；KU Leuven（鲁汶大学）
这项工作解决了具有挑战性的任务，基于激光雷达的三维目标检测在雾天。在这样的场景中收集和注释数据是非常耗时、费力和成本密集的。在本文中，我们通过将物理上精确的雾模拟到晴朗的天气场景中来解决这个问题，以便在晴朗的天气中捕获的丰富的现有真实数据集可以重新用于我们的任务。我们的贡献是双重的：1）我们开发了一个物理上有效的雾模拟方法，适用于任何激光雷达数据集。这释放了大规模模糊训练数据的获取，而无需额外的成本。这些部分合成数据可以用于提高几种感知方法的鲁棒性，例如3D目标检测和跟踪或同时定位与地图构建。2)通过大量的实验与几个国家的最先进的检测方法，我们表明，我们的雾模拟可以利用显着提高性能的三维目标检测中存在的雾。因此，我们率先在Seeing Through Fog数据集上提供强大的3D目标检测基线。我们的代码可在www.trace.ethz.ch/lidar_fog_simulation上获得。
CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weather
School of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；USC Viterbi School of Engineering, the University of Southern California（南加州大学维特比工程学院）；College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；School of Robotics, Hunan University（湖南大学机器人学院）
Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time
Institute for Automotive Engineering RWTH Aachen University（亚琛工业大学汽车工程研究所）；Institute of Imaging and Computer Vision RWTH Aachen University（亚琛工业大学图像与计算机视觉研究所）
In Rain or Shine: Understanding and Overcoming Dataset Bias for Improving Robustness Against Weather Corruptions for Autonomous Vehicles
Carnegie Mellon University（卡内基梅隆大学）；Symbiosis Institute of Technology (SIT), Symbiosis International (Deemed University)（共生技术学院，共生国际（视为大学））；Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis International (Deemed University)（共生应用人工智能中心，共生国际（视为大学））
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
Nanyang Technological University（南洋理工大学）；East China Normal University（华东师范大学）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；New York University（纽约大学）
Enhancing Robustness of Human Detection Algorithms in Maritime SAR through Augmented Aerial Images to Simulate Weather Conditions
Jakarta Intercultural School（雅加达国际学校）；Busan Foreign School（釜山外国语学校）；SMPK 8 Penabur Tanjung Duren（丹戎杜伦佩纳布尔8号初中（基督教学校））；Avon High School（雅芳高中）；Algoverse AI Research（Algoverse人工智能研究院）
ReviveDiff: A Universal Diffusion Model for Restoring Images in Adverse Weather Conditions
Faculty of Engineering and Information Technology, University of Technology Sydney（工程与信息技术学院，技术悉尼大学）；PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology（智能感知与高维信息系统教育部重点实验室，计算机科学与工程学院，南京理工大学）；Key Laboratory of Artificial Intelligence, Ministry of Education（人工智能教育部重点实验室）
Robust Single Object Tracking in LiDAR Point Clouds under Adverse Weather Conditions
School of Mathematical Sciences, Dalian University of Technology（大连理工大学数学科学学院）；School of Economics and Management, China University of Mining and Technology（中国矿业大学经济管理学院）；DUT-BSU Joint Institute, Dalian University of Technology（大连理工大学-白俄罗斯国立大学联合学院）
Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather
School of Xingzhi College, South China Normal University（星智学院，华南师范大学）；College of Big Data and Internet, Shenzhen Technology University（大数据与互联网学院，深圳科技大学）；School of Data Science and Engineering, Xingzhi College, South China Normal University（数据科学与工程学院，星智学院，华南师范大学）；Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology（电子与计算机工程系，香港科技大学）；College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学）
