论文标题
单眼3D对象检测的密集约束深度估计器
Densely Constrained Depth Estimator for Monocular 3D Object Detection
论文作者
论文摘要
由于缺乏深度，从单眼图像估算物体的准确3D位置是一个具有挑战性的问题。先前的工作表明，利用对象的关键点投影约束来估计多个深度候选者可以提高检测性能。但是，现有方法只能利用垂直边缘作为深度估计的投影约束。因此，这些方法仅使用少量投影约束并产生不足的深度候选物，从而导致深度估计不准确。在本文中，我们提出了一种利用任何方向边缘的密集投影约束的方法。这样，我们采用了更多的投影限制并产生相当大的候选者。此外，我们提供一个匹配加权模块以合并深度候选者的图形。提出的方法DCD（密度约束的检测器）在KITTI和WOD基准测试中实现了最先进的性能。代码在https://github.com/bravegroup/dcd上发布。
Estimating accurate 3D locations of objects from monocular images is a challenging problem because of lacking depth. Previous work shows that utilizing the object's keypoint projection constraints to estimate multiple depth candidates boosts the detection performance. However, the existing methods can only utilize vertical edges as projection constraints for depth estimation. So these methods only use a small number of projection constraints and produce insufficient depth candidates, leading to inaccurate depth estimation. In this paper, we propose a method that utilizes dense projection constraints from edges of any direction. In this way, we employ much more projection constraints and produce considerable depth candidates. Besides, we present a graph matching weighting module to merge the depth candidates. The proposed method DCD (Densely Constrained Detector) achieves state-of-the-art performance on the KITTI and WOD benchmarks. Code is released at https://github.com/BraveGroup/DCD.
