MonoEdge: Monocular 3D Object Detection Using Local Perspectives
This work addresses 3D object detection from single images, a key problem in autonomous driving and robotics, with an incremental improvement by incorporating local perspectives into existing frameworks.
The paper tackles monocular 3D object detection by leveraging local perspective effects, which are often overlooked, and achieves superior performance over strong baselines on multiple datasets.
We propose a novel approach for monocular 3D object detection by leveraging local perspective effects of each object. While the global perspective effect shown as size and position variations has been exploited for monocular 3D detection extensively, the local perspectives has long been overlooked. We design a local perspective module to regress a newly defined variable named keyedge-ratios as the parameterization of the local shape distortion to account for the local perspective, and derive the object depth and yaw angle from it. Theoretically, this module does not rely on the pixel-wise size or position in the image of the objects, therefore independent of the camera intrinsic parameters. By plugging this module in existing monocular 3D object detection frameworks, we incorporate the local perspective distortion with global perspective effect for monocular 3D reasoning, and we demonstrate the effectiveness and superior performance over strong baseline methods in multiple datasets.