Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Unsupervised scale-consistent depth learning from video
Author: Bian, J.
Zhan, H.
Wang, N.
Li, Z.
Zhang, L.
Shen, C.
Cheng, M.-M.
Reid, I.
Citation: International Journal of Computer Vision, 2021; 129(9):2548-2564
Publisher: Springer Nature
Issue Date: 2021
ISSN: 0920-5691
Statement of
Jia-Wang Bian, Huangying Zhan, Naiyan Wang, Zhichao Li, Le Zhang, Chunhua Shen, Ming-Ming Cheng, Ian Reid
Abstract: We propose a monocular depth estimation method SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time. Our contributions include: (i) we propose a geometry consistency loss, which penalizes the inconsistency of predicted depths between adjacent views; (ii) we propose a self-discovered mask to automatically localize moving objects that violate the underlying static scene assumption and cause noisy signals during training; (iii) we demonstrate the efficacy of each component with a detailed ablation study and show high-quality depth estimation results in both KITTI and NYUv2 datasets. Moreover, thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into ORB-SLAM2 system for more robust and accurate tracking. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training. Finally, we provide several demos for qualitative evaluation. The source code is released on GitHub.
Keywords: Unsupervised depth estimation; scale consistency; visual SLAM; pseudo-RGBD SLAM
Rights: © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021
DOI: 10.1007/s11263-021-01484-6
Grant ID:
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.