Abstract
To alleviate the need of expensive depth annotations, some existing works resort to unsupervised learning methods for depth estimation using monocular videos. To improve the accuracy of the prediction with the relationship of the inter-frame, we present a new unsupervised learning algorithm for monocular depth estimation. In contrast to most existing works, our method predicts depth maps for both target and source frames in each iteration. An inter-frame depth interpolation module is designed, which learns to infer the depth map of the target frame based on those of the source frames. A temporal consistency loss is also proposed to penalize the discrepancy of the predicted depth maps across frames, which not only enforces the coherence of video depth prediction but also provides supervision to source view depth estimation. Similar to the idea of the mutual learning, our method takes full advantages of both target and source views for depth estimation learning. Each module of our proposed method is differentiable, allowing end-to-end training of the whole system. Experiments on the popular KITTI dataset have been conducted and shown that our method performs favorably against state-of-the-art approaches.
Supported by the National Natural Science Foundation of China 61771088.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bian, J.W., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: Thirty-Third Conference on Neural Information Processing Systems (NeurIPS), pp. 35–45 (2019)
Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8001–8008 (2019)
Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, vol. 27, pp. 2366–2374 (2014)
Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740–756. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_45
Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. (IJRR) 32(11), 1231–1237 (2013)
Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6602–6611 (2017)
Godard, C., Oisin, M.A., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: The IEEE International Conference on Computer Vision (ICCV), pp. 3827–3837 (2019)
Klodt, M., Vedaldi, A.: Supervising the new with the old: learning SFM from SFM. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 713–728. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_43
Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024–2039 (2015)
Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5667–5675 (2018)
Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4040–4048 (2016)
Mehta, I., Sakurikar, P., Narayanan, P.: Structured adversarial training for unsupervised monocular depth estimation. In: 2018 International Conference on 3D Vision (3DV), pp. 314–323 (2018)
Poggi, M., Tosi, F., Mattoccia, S.: Learning monocular depth estimation with unsupervised trinocular assumptions. In: 2018 International Conference on 3D Vision (3DV), pp. 324–333 (2018)
Ranjan, A., et al.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12232–12241 (2019)
Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824–840 (2008)
Wang, C., Miguel Buenaposada, J., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2022–2030 (2018)
Yang, Z., Wang, P., Wang, Y., Xu, W., Nevatia, R.: LEGO: learning edge with geometry all at once by watching videos. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 225–234 (2018)
Yang, Z., Wang, P., Xu, W., Zhao, L., Nevatia, R.: Unsupervised learning of geometry from videos with edge-aware depth-normal consistency. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, pp. 7493–7500 (2018)
Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1983–1992 (2018)
Zhan, H., Garg, R., Saroj Weerasekera, C., Li, K., Agarwal, H., Reid, I.: Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 340–349 (2018)
Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: CVPR, pp. 4320–4328 (2018)
Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6612–6619 (2017)
Zou, Y., Luo, Z., Huang, J.-B.: DF-Net: unsupervised joint learning of depth and flow using cross-task consistency. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 38–55. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_3
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, M., Li, J. (2021). Efficient Unsupervised Monocular Depth Estimation with Inter-Frame Depth Interpolation. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12890. Springer, Cham. https://doi.org/10.1007/978-3-030-87361-5_59
Download citation
DOI: https://doi.org/10.1007/978-3-030-87361-5_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87360-8
Online ISBN: 978-3-030-87361-5
eBook Packages: Computer ScienceComputer Science (R0)