论文标题
ORA3D：重叠区域意识到多视图3D对象检测
ORA3D: Overlap Region Aware Multi-view 3D Object Detection
论文作者
论文摘要
当前的多视图3D对象检测方法通常无法正确检测重叠区域中的对象，并且网络对场景的理解通常仅限于单眼检测网络。此外，重叠区域中的物体通常会在很大程度上被遮住或因摄像机失真而造成变形，从而导致域移动。为了减轻此问题，我们建议使用以下两个主要模块：（1）弱深度监督和（2）对抗重叠区域歧视器的立体视差估计。前者利用传统的立体声差异估计方法从重叠区域获得可靠的差异信息。鉴于差异估计为监督，我们建议将网络正规化以充分利用双眼图像的几何潜力并相应地提高整体检测准确性。此外，后一个模块最大程度地减少了非重叠区域和重叠区域之间的代表性差距。我们用Nuscenes大规模多视图3D对象检测数据证明了所提出的方法的有效性。我们的实验表明，我们提出的方法的表现优于当前最新模型，即detr3d和bevdet。
Current multi-view 3D object detection methods often fail to detect objects in the overlap region properly, and the networks' understanding of the scene is often limited to that of a monocular detection network. Moreover, objects in the overlap region are often largely occluded or suffer from deformation due to camera distortion, causing a domain shift. To mitigate this issue, we propose using the following two main modules: (1) Stereo Disparity Estimation for Weak Depth Supervision and (2) Adversarial Overlap Region Discriminator. The former utilizes the traditional stereo disparity estimation method to obtain reliable disparity information from the overlap region. Given the disparity estimates as supervision, we propose regularizing the network to fully utilize the geometric potential of binocular images and improve the overall detection accuracy accordingly. Further, the latter module minimizes the representational gap between non-overlap and overlapping regions. We demonstrate the effectiveness of the proposed method with the nuScenes large-scale multi-view 3D object detection data. Our experiments show that our proposed method outperforms current state-of-the-art models, i.e., DETR3D and BEVDet.
