The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets often contain data that are meticulously cleaned. Such configurations, however, cannot reflect the reliability of perception models during the deployment stage. In this work, we present Robo3D, the first comprehensive benchmark heading toward probing the robustness of 3D detectors and segmentors under out-of-distribution scenarios against natural corruptions that occur in real-world environments. Specifically, we consider eight corruption types stemming from adversarial weather conditions, external disturbances, and internal sensor failure. We uncover that, although promising results have been progressively achieved on standard benchmarks, state-of-the-art 3D perception models are at risk of being vulnerable to corruptions. We draw key observations on the use of data representations, augmentation schemes, and training strategies, that could severely affect the model's performance. To pursue better robustness, we propose a density-insensitive training framework along with a simple flexible voxelization strategy to enhance the model resiliency. We hope our benchmark and approach could inspire future research in designing more robust and reliable 3D perception models. Our robustness benchmark suite is publicly available.

翻译：三维感知系统在环境与传感器自然干扰下的鲁棒性对安全关键型应用至关重要。现有大规模三维感知数据集通常包含经过精细清洁的数据，但这种配置无法反映部署阶段感知模型的可靠性。本文提出Robo3D——首个系统评估三维检测器和分割器在真实环境自然干扰所引发的分布外场景下鲁棒性的综合基准。具体而言，我们考虑了源自恶劣天气条件、外部扰动及内部传感器故障的八种干扰类型。研究发现，尽管在标准基准上已逐步取得显著成果，但最先进的三维感知模型仍存在易受干扰影响的风险。我们基于数据表征、增强方案及训练策略等关键观察，揭示了这些因素可能严重制约模型性能的关键影响。为追求更优鲁棒性，我们提出了一种密度不敏感训练框架，并结合简单灵活体素化策略以增强模型抗干扰能力。期望本基准与方法能启发未来设计更鲁棒可靠的三维感知模型。本鲁棒性基准套件现已公开。