Monocular Depth Prediction through Continuous 3D Loss

Autor:	Zhu, Minghan, Ghaffari, Maani, Zhong, Yuanxin, Lu, Pingping, Cao, Zhong, Eustice, Ryan M., Peng, Huei
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: 8 pages, 4 figures. Accepted by IROS 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2003.09763 Zobrazit plný text záznamu View this record from Arxiv