Exploring 2D Data Augmentation for 3D Monocular Object Detection
This work addresses a gap in data augmentation techniques for 3D object detection, which is incremental as it adapts 2D methods to improve performance in a specific domain.
The paper tackles the problem of data augmentation for 3D monocular object detection by evaluating existing 2D augmentations and proposing two novel ones that do not require novel view synthesis, resulting in a 4% improvement in 3D AP for cars and about 1.8% for pedestrians and cyclists on the KITTI dataset.
Data augmentation is a key component of CNN based image recognition tasks like object detection. However, it is relatively less explored for 3D object detection. Many standard 2D object detection data augmentation techniques do not extend to 3D box. Extension of these data augmentations for 3D object detection requires adaptation of the 3D geometry of the input scene and synthesis of new viewpoints. This requires accurate depth information of the scene which may not be always available. In this paper, we evaluate existing 2D data augmentations and propose two novel augmentations for monocular 3D detection without a requirement for novel view synthesis. We evaluate these augmentations on the RTM3D detection model firstly due to the shorter training times . We obtain a consistent improvement by 4% in the 3D AP (@IoU=0.7) for cars, ~1.8% scores 3D AP (@IoU=0.25) for pedestrians & cyclists, over the baseline on KITTI car detection dataset. We also demonstrate a rigorous evaluation of the mAP scores by re-weighting them to take into account the class imbalance in the KITTI validation dataset.