Bian, J.-W., Zhan, H., Wang, N., Li, Z., Zhang, L., Shen, C., … Reid, I. (2021). Unsupervised Scale-Consistent Depth Learning from Video. International Journal of Computer Vision. doi:10.1007/s11263-021-01484-6
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.
This work was in part supported by the Australian Centre of Excellence for Robotic Vision CE140100016, and the ARC Laureate Fellowship FL130100102 to Prof. Ian Reid. This work was supported by Major Project for New Generation of AI (No. 2018AAA0100403), Tianjin
Natural Science Foundation (No. 18JCYBJC41300 and No. 18ZXZNGX00110), and NSFC (61922046) to Prof. Ming-Ming Cheng.