MonoGRNet: A General Framework for Monocular 3D Object Detection
This addresses 3D scene understanding for autonomous driving and robotics, but appears incremental as it builds on existing geometric reasoning approaches.
The authors tackled monocular 3D object detection by proposing MonoGRNet, which decomposes the task into four sub-tasks and achieves efficient prediction without object proposals or pixel-level depth estimation, showing promising performance on KITTI, Cityscapes, and MS COCO datasets.
Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a monocular image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet decomposes the monocular 3D object detection task into four sub-tasks including 2D object detection, instance-level depth estimation, projected 3D center estimation and local corner regression. The task decomposition significantly facilitates the monocular 3D object detection, allowing the target 3D bounding boxes to be efficiently predicted in a single forward pass, without using object proposals, post-processing or the computationally expensive pixel-level depth estimation utilized by previous methods. In addition, MonoGRNet flexibly adapts to both fully and weakly supervised learning, which improves the feasibility of our framework in diverse settings. Experiments are conducted on KITTI, Cityscapes and MS COCO datasets. Results demonstrate the promising performance of our framework in various scenarios.