论文标题
通过连续3D损失进行单眼深度预测
Monocular Depth Prediction through Continuous 3D Loss
论文作者
论文摘要
本文报告了从单眼图像中学习深度的新连续3D损失函数。单眼图像的密集深度预测是使用稀疏激光点监督的，这使我们能够在训练过程中利用带摄像头传感器套件的可用开源数据集。当前，准确且负担得起的范围传感器不容易获得。立体声摄像机和激光镜头的深度不准确或稀疏/昂贵。与当前的点对点损失评估方法相反，拟议的3D损失将点云视为连续对象。因此，由于激光雷达的稀疏度测量值，它弥补了缺乏密集的地面真相深度。我们将拟议损失应用于三种最先进的单眼深度预测方法DORN，BTS和MonoDepth2。实验评估表明，与所有测试的基准相比，提出的损失提高了深度预测准确性，并产生具有更一致的3D几何结构的点云，这意味着拟议损失对一般深度预测网络的益处。可以在https://youtu.be/5hl8bjsay4y上获得此工作的视频演示。
This paper reports a new continuous 3D loss function for learning depth from monocular images. The dense depth prediction from a monocular image is supervised using sparse LIDAR points, which enables us to leverage available open source datasets with camera-LIDAR sensor suites during training. Currently, accurate and affordable range sensor is not readily available. Stereo cameras and LIDARs measure depth either inaccurately or sparsely/costly. In contrast to the current point-to-point loss evaluation approach, the proposed 3D loss treats point clouds as continuous objects; therefore, it compensates for the lack of dense ground truth depth due to LIDAR's sparsity measurements. We applied the proposed loss in three state-of-the-art monocular depth prediction approaches DORN, BTS, and Monodepth2. Experimental evaluation shows that the proposed loss improves the depth prediction accuracy and produces point-clouds with more consistent 3D geometric structures compared with all tested baselines, implying the benefit of the proposed loss on general depth prediction networks. A video demo of this work is available at https://youtu.be/5HL8BjSAY4Y.
