Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
复制标题
使用深度神经网络的左右一致性半监督单目深度估计
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Hong Zhang
中科院分区：
文献类型：
--
作者：
A. Amiri;S. Loo;Hong Zhang
从单目相机图像中估计景深的研究取得了巨大的进展。现有的单图像深度预测方法完全基于深度神经网络，它们的训练可以使用立体图像对进行无监督，使用激光雷达点云进行监督，或者使用立体和激光雷达进行半监督。一般来说，半监督训练是首选，因为它没有监督训练的缺点，即由于相机和lidar视野的差异而导致的缺点，也没有无监督训练的缺点，即由于可以从立体对恢复的深度精度较差而导致的缺点。在本文中，我们介绍了我们在使用半监督训练的单图像深度预测方面的研究，该研究优于最先进的技术。我们通过一个损失函数来实现这一点，该函数明确地利用了立体重建中的左右一致性，这在以前的半监督训练中没有被采用。此外，我们描述了正确使用激光雷达获得的地面真值深度，可以显着减少预测误差。在流行的数据集上评估了我们的深度预测模型的性能，并通过实验结果证明了我们的半监督训练方法的每个方面的重要性。我们的深度神经网络模型已经公开了。
There has been tremendous research progress in estimating the depth of a scene from a monocular camera image. Existing methods for single-image depth prediction are exclusively based on deep neural networks, and their training can be unsupervised using stereo image pairs, supervised using LiDAR point clouds, or semi-supervised using both stereo and LiDAR. In general, semi-supervised training is preferred as it does not suffer from the weaknesses of either supervised training, resulting from the difference in the cameras and the LiDARs field of view, or unsupervised training, resulting from the poor depth accuracy that can be recovered from a stereo pair. In this paper, we present our research in single-image depth prediction using semi-supervised training that outperforms the state-of-the-art. We achieve this through a loss function that explicitly exploits left-right consistency in a stereo reconstruction, which has not been adopted in previous semi-supervised training. In addition, we describe the correct use of ground truth depth derived from LiDAR that can significantly reduce prediction error. The performance of our depth prediction model is evaluated on popular datasets, and the importance of each aspect of our semi-supervised training approach is demonstrated through experimental results. Our deep neural network model has been made publicly available.1.