论文标题
Monoground：从地面检测单眼3D对象
MonoGround: Detecting Monocular 3D Objects from the Ground
论文作者
论文摘要
单眼3D对象检测因其在简单性和成本方面的优势而引起了极大的关注。由于单眼成像过程的2D至3D映射本质不足，因此单眼3D对象检测的深度估计不准确，因此3D检测结果较差。为了减轻这个问题，我们建议将地面引入单眼3D对象检测中的先验。地面先验是对不足的映射的额外几何条件，并且是深度估计的额外来源。这样，我们可以从地面获得更准确的深度估计。同时，要获得地面平面的充分优势，我们提出了一种深度对准训练策略，并提出了针对接地平面量身定制的精确的两阶段深度推理方法。值得注意的是，引入的地面之前不需要额外的数据源，例如LIDAR，立体声图像和深度信息。 Kitti基准测试的广泛实验表明，与其他方法相比，我们的方法可以在保持非常快的速度的同时获得最先进的结果。我们的代码和型号可在https://github.com/cfzd/monoground上找到。
Monocular 3D object detection has attracted great attention for its advantages in simplicity and cost. Due to the ill-posed 2D to 3D mapping essence from the monocular imaging process, monocular 3D object detection suffers from inaccurate depth estimation and thus has poor 3D detection results. To alleviate this problem, we propose to introduce the ground plane as a prior in the monocular 3d object detection. The ground plane prior serves as an additional geometric condition to the ill-posed mapping and an extra source in depth estimation. In this way, we can get a more accurate depth estimation from the ground. Meanwhile, to take full advantage of the ground plane prior, we propose a depth-align training strategy and a precise two-stage depth inference method tailored for the ground plane prior. It is worth noting that the introduced ground plane prior requires no extra data sources like LiDAR, stereo images, and depth information. Extensive experiments on the KITTI benchmark show that our method could achieve state-of-the-art results compared with other methods while maintaining a very fast speed. Our code and models are available at https://github.com/cfzd/MonoGround.
