As 3D object detection on point clouds relies on the geometrical relationships between the points, non-standard object shapes can hinder a method's detection capability. However, in safety-critical settings, robustness to out-of-domain and long-tail samples is fundamental to circumvent dangerous issues, such as the misdetection of damaged or rare cars. In this work, we substantially improve the generalization of 3D object detectors to out-of-domain data by deforming point clouds during training. We achieve this with 3D-VField: a novel data augmentation method that plausibly deforms objects via vector fields learned in an adversarial fashion. Our approach constrains 3D points to slide along their sensor view rays while neither adding nor removing any of them. The obtained vectors are transferable, sample-independent and preserve shape and occlusions. Despite training only on a standard dataset, such as KITTI, augmenting with our vector fields significantly improves the generalization to differently shaped objects and scenes. Towards this end, we propose and share CrashD: a synthetic dataset of realistic damaged and rare cars, with a variety of crash scenarios. Extensive experiments on KITTI, Waymo, our CrashD and SUN RGB-D show the generalizability of our techniques to out-of-domain data, different models and sensors, namely LiDAR and ToF cameras, for both indoor and outdoor scenes. Our CrashD dataset is available at https://crashd-cars.github.io.
翻译:由于点云上的三维天体探测取决于各点之间的几何关系,非标准天体形状会妨碍方法的检测能力。 但是,在安全关键环境下,对外侧和长尾抽样的稳健性对于绕过危险问题,例如对损坏或稀有汽车的误发现至关重要。 在这项工作中,我们通过在训练期间对点云进行变形,大大改进三维天体探测器对外侧数据的一般化。我们用3D-V字段实现这一点:一种新的数据增强方法,通过对抗性模式学习的矢量字段,可以令人相信地变形物体。在安全关键环境下,我们的方法限制三维点沿着传感器的视线滑动,而既不增加也不删除其中任何一个。获得的矢量是可转让的、不依赖的、保存形状和封闭的。尽管只有KITTI(KITTI)等标准数据集的培训,与我们的矢量场一起大大改进了对不同形状的物体和场景象。到此端,我们提议并分享克拉D(C-LAR-D)的合成数据集成的C-C-ROD-ROD-RO-L-L-L-L-D-D-ROD-L-LV-D-S-Laservil-LV-LV-LV-S-S-S-S-S-LV-S-S-LV-LV-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-LV-LV-S-S-S-S-LV-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-