Understanding the world in 3D is a critical component of urban autonomous
driving. Generally, the combination of expensive LiDAR sensors and stereo RGB
imaging has been paramount for successful 3D object detection algorithms,
whereas monocular image-only methods experience drastically reduced
performance. We propose to reduce the gap by reformulating the monocular 3D
detection problem as a standalone 3D region proposal network. We leverage the
geometric relationship of 2D and 3D perspectives, allowing 3D boxes to utilize
well-known and powerful convolutional features generated in the image-space. To
help address the strenuous 3D parameter estimations, we further design
depth-aware convolutional layers which enable location specific feature
development and in consequence improved 3D scene understanding. Compared to
prior work in monocular 3D detection, our method consists of only the proposed
3D region proposal network rather than relying on external networks, data, or
multiple stages. M3D-RPN is able to significantly improve the performance of
both monocular 3D Object Detection and Bird's Eye View tasks within the KITTI
urban autonomous driving dataset, while efficiently using a shared multi-class
model.

本研究提出了一种基于几何关系的 monocular 三维物体检测方法，通过单独的三维区域建议网络和深度感知卷积层，能够有效地改善基于图像的三维物体检测在自动驾驶领域中的表现。在 KITTI 数据集上，与其他之前的方法相比，M3D-RPN 方法在单眼三维物体检测和俯视图检测任务中都表现出显著的性能提升。