Abstract
Robust monocular depth estimation (MDE) aims at learning a unified model that works across diverse real-world scenes, which is an important and active topic in computer vision. In this paper, we present Megatron_RVC, our winning solution for the monocular depth challenge in the Robust Vision Challenge (RVC) 2022, where we tackle the challenging problem from three perspectives: network architecture, training strategy and dataset. In particular, we made three contributions towards robust MDE: (1) we built a neural network with high capacity to enable flexible and accurate monocular depth predictions, which contains dedicated components to provide content-aware embeddings and to improve the richness of the details; (2) we proposed a novel mixing training strategy to handle real-world images with different aspect ratios, resolutions and apply tailored loss functions based on the properties of their depth maps; (3) to train a unified network model that covers diverse real-world scenes, we used over 1 million images from different datasets. As of 3rd October 2022, our unified model ranked consistently first across three benchmarks (KITTI, MPI Sintel, and VIPER) among all participants.
Similar content being viewed by others
Data Availability
All data generated or analysed during this study are included in articles or links in Table 1.
References
Abdulwahab, S., Rashwan, H. A., Garcia, M. A., Masoumian, A., & Puig, D. (2022). Monocular depth map estimation based on a multi-scale deep architecture and curvilinear saliency feature boosting. Neural Computing and Applications, 34(19), 16423–16440.
Alhashim, I., & Wonka, P. (2018). High quality monocular depth estimation via transfer learning. arXiv preprint arXiv:1812.11941
Atapour-Abarghouei, A., & Breckon, T. P. (2018). Real-time monocular depth estimation using synthetic data with domain adaptation via image style transfer. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2800–2810).
Bhat, S. F., Alhashim, I., & Wonka, P. (2021). Adabins: Depth estimation using adaptive bins. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4009–4018).
Butler, D. J., Wulff, J., Stanley, G. B., & Black, M. J. (2012). A naturalistic open source movie for optical flow evaluation. In European conference on computer vision (ECCV) (pp. 611–625).
Cabon, Y., Murray, N., & Humenberger, M. (2020). Virtual KITTI 2. arXiv preprint arXiv:2001.10773
Chen, W., Fu, Z., Yang, D., & Deng, J. (2016). Single-image depth perception in the wild. In Advances in neural information processing systems (NeurIPS) (vol. 29).
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3213–3223).
Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 248–255).
Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Yuan, L., Chen, D., & Guo, B. (2022). CSWin transformer: A general vision transformer backbone with cross-shaped windows. In IEEE conference on computer vision and pattern recognition (CVPR) (pp 12124–12134).
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations (ICLR).
Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. In Advances in neural information processing systems (NeurIPS) (vol. 27).
Facil, J. M., Ummenhofer, B., Zhou, H., Montesano, L., Brox, T., & Civera, J. (2019). CAM-convs: Camera-aware multi-scale convolutions for single-view depth. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 11826–11835).
Fu, H., Gong, M., Wang, C., Batmanghelich, K., & Tao, D. (2018). Deep ordinal regression network for monocular depth estimation. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2002–2011).
Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016). Virtual worlds as proxy for multi-object tracking analysis. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4340–4349).
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The KITTI dataset. The International Journal of Robotics Research, 32(11), 1231–1237.
Godard, C., Mac Aodha, O., & Brostow, G. J. (2017). Unsupervised monocular depth estimation with left-right consistency. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 270–279).
Godard, C., Mac Aodha, O., Firman, M., & Brostow, G. J. (2019). Digging into self-supervised monocular depth estimation. In IEEE international conference on computer vision (ICCV) (pp. 3828–3838).
Gta5-depth-estimation, Retrieved July 26, 2022. https://github.com/gta5-vision/GTA5-depth-estimation
Han, K., Wang, Y., Guo, J., Tang, Y., & Wu, E. (2022). Vision GNN: An image is worth graph of nodes. arXiv preprint arXiv:2206.00272
He, M., Hui, L., Bian, Y., Ren, J., Xie, J., & Yang, J. (2022). RA-depth: Resolution adaptive self-supervised monocular depth estimation. In European conference on computer vision (ECCV) (pp. 565–581).
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770–778).
Hua, Y., Kohli, P., Uplavikar, P., Ravi, A., Gunaseelan, S., Orozco, J., & Li, E. (2020). Holopix50k: A large-scale in-the-wild stereo image dataset. arXiv preprint arXiv:2003.11172
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4700–4708).
Hurl, B., Czarnecki, K., & Waslander, S. (2019). Precise synthetic image and LiDAR (PreSIL) dataset for autonomous vehicle perception. In IEEE intelligent vehicles symposium (IV) (pp. 2522–2529).
Ji, P., Li, R., Bhanu, B., & Xu, Y. (2021). MonoIndoor: Towards good practice of self-supervised monocular depth estimation for indoor environments. In IEEE international conference on computer vision (ICCV) (pp. 12787–12796).
Kim, Y., Ham, B., Oh, C., & Sohn, K. (2016). Structure selective depth superresolution for RGB-D cameras. IEEE Transactions on Image Processing (TIP), 25(11), 5227–5238.
Kopf, J., Rong, X., & Huang, J. B. (2021). Robust consistent video depth estimation. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1611–1621).
Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N. (2016). Deeper depth prediction with fully convolutional residual networks. In International conference on 3D vision (3DV) (pp. 239–248).
Le, H. A., Mensink, T., Das, P., Karaoglu, S., & Gevers, T. (2021) EDEN: Multimodal synthetic dataset of enclosed garden scenes. In IEEE winter conference on applications of computer vision (WACV) (pp. 1579–1589).
Lee, J. H., Han, M. K., Ko, D. W., & Suh, I. H. (2019). From big to small: Multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326
Li, Z., & Snavely, N. (2018). MegaDepth: Learning single-view depth prediction from internet photos. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2041–2050).
Li, Z., Dekel, T., Cole, F., Tucker, R., Snavely, N., Liu, C., & Freeman, W. T. (2019). Learning the depths of moving people by watching frozen people. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4521–4530).
Li, B., Huang, Y., Liu, Z., Zou, D., & Yu, W. (2021). StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation. In IEEE international conference on computer vision (ICCV) (pp. 12663–12673).
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., Wei, F., & Guo, B. (2022). Swin transformer v2: Scaling up capacity and resolution. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 12009–12019).
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In IEEE international conference on computer vision (ICCV) (pp. 10012–10022).
Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A convnet for the 2020s. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 11976–11986).
Luo, X., Huang, J. B., Szeliski, R., Matzen, K., & Kopf, J. (2020). Consistent video depth estimation. ACM Transactions on Graphics (ToG), 39(4), 71–1.
Masoumian, A., Rashwan, H. A., Abdulwahab, S., Cristiano, J., Asif, M. S., & Puig, D. (2023). GCNDepth: Self-supervised monocular depth estimation based on graph convolutional network. Neurocomputing, 517, 81–92.
Masoumian, A., Rashwan, H. A., Cristiano, J., Asif, M. S., & Puig, D. (2022). Monocular depth estimation using deep learning: A review. Sensors, 22(14), 5353.
Mehta, S., & Rastegari, M. (2021). MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. In International conference on learning representations (ICLR).
Miangoleh, S. M. H., Dille, S., Mai, L., Paris, S., & Aksoy, Y. (2021). Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 9685–9694)
Ming, Y., Meng, X., Fan, C., & Yu, H. (2021). Deep learning for monocular depth estimation: A review. Neurocomputing, 438, 14–33.
Quinonero-Candela, J., Sugiyama, M., Schwaighofer, A., & Lawrence, N. D. (2008). Dataset shift in machine learning. MIT Press.
Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021). Vision transformers for dense prediction. In IEEE international conference on computer vision (ICCV) (pp. 12179–12188).
Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., & Koltun, V. (2020). Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(3), 1623–1637.
Ren, H., Raj, A., El-Khamy, M., & Lee, J. (2020). SUW-Learn: Joint supervised, unsupervised, weakly supervised deep learning for monocular depth estimation. In IEEE conference on computer vision and pattern recognition (CVPR) workshop (pp. 750–751).
Richter, S. R., Hayder, Z., & Koltun, V. (2017). Playing for benchmarks. In IEEE international conference on computer vision (ICCV) (pp. 2232–2241).
Saxena, A., Sun, M., & Ng, A. Y. (2008). Make3D: Learning 3D scene structure from a single still image. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 31(5), 824–840.
Schonberger, J. L., & Frahm, J. M. (2016). Structure-from-motion revisited. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4104–4113).
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In European conference on computer vision (ECCV) (pp. 746–760).
Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (ICML) (pp. 6105–6114).
Teed, Z., & Deng, J. (2020). RAFT: Recurrent all-pairs field transforms for optical flow. In European conference on computer vision (ECCV) (pp. 402–419).
The robust vision challenge (2022). http://www.robustvision.net
Torralba, A., & Efros, A. A. (2011). Unbiased look at dataset bias. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1521–1528).
Ummenhofer, B., Zhou, H., Uhrig, J., Mayer, N., Ilg, E., Dosovitskiy, A., & Brox, T. (2017). DeMoN: Depth and motion network for learning monocular stereo. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5038–5047).
Van Den Oord, A., & Vinyals, O. (2017). Neural discrete representation learning. In Advances in neural information processing systems (NeurIPS) (vol. 30).
Vasiljevic, I., Kolkin, N., Zhang, S., Luo, R., Wang, H., Dai, F. Z., Daniele, A. F., Mostajabi, M., Basart, S., & Walter, M. R., Shakhnarovich, G. (2019). Diode: A dense indoor and outdoor depth dataset. arXiv preprint arXiv:1908.00463
Vyas, P., Saxena, C., Badapanda, A., & Goswami, A. (2022). Outdoor monocular depth estimation: A research review. arXiv preprint arXiv:2205.01399
Wang, C., Lucey, S., Perazzi, F., & Wang, O. (2019). Web stereo video supervision for depth prediction from dynamic scenes. In International conference on 3D vision (3DV) (pp. 348–357).
Wang, X., Yin, W., Kong, T., Jiang, Y., Li, L., & Shen, C. (2020). Task-aware monocular depth estimation for 3d object detection. In AAAI conference on artificial intelligence (AAAI) (vol. 34, pp. 12257–12264).
Wu, C.Y., Wang, J., Hall, M., Neumann, U., & Su, S. (2022). Toward practical monocular indoor depth estimation. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3814–3824).
Xian, K., Shen, C., Cao, Z., Lu, H., Xiao, Y., Li, R., & Luo, Z. (2018). Monocular relative depth perception with web stereo data supervision. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 311–320).
Xian, K., Zhang, J., Wang, O., Mai, L., Lin, Z., & Cao, Z. (2020). Structure-guided ranking loss for single image depth prediction. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 611–620).
Xu, G., Yin, W., Chen, H., Cheng, K., Zhao, F., & Shen, C. (2022). Boosting monocular depth estimation with sparse guided points. arXiv preprint arXiv:2202.01470
Xu, G., Yin, W., Chen, H., Shen, C., Cheng, K., & Zhao, F. (2023). Pose-free 3d scene reconstruction with frozen depth models. In IEEE international conference on computer vision (ICCV).
Yin, W., Zhang, C., Chen, H., Cai, Z., Yu, G., Wang, K., Chen, X., & Shen, C. (2023). Metric3D: Towards zero-shot metric 3d prediction from a single image. In IEEE international conference on computer vision (ICCV).
Yin, W., Zhang, J., Wang, O., Niklaus, S., Mai, L., Chen, S., & Shen, C. (2021). Learning to recover 3d scene shape from a single image. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 204–213).
Yin, W., Liu, Y., & Shen, C. (2021). Virtual normal: Enforcing geometric constraints for accurate and robust depth prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(10), 7282–7295.
Yuan, W., Gu, X., Dai, Z., Zhu, S., & Tan, P. (2022). Neural window fully-connected CRFs for monocular depth estimation. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3916–3925).
Zhan, H., Garg, R., Weerasekera, C. S., Li, K., Agarwal, H., & Reid, I. (2018). Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 340–349).
Zhang, Z., Lathuiliere, S., Ricci, E., Sebe, N., Yan, Y., & Yang, J. (2020). Online depth learning against forgetting in monocular videos. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4494–4503).
Zhao, S., Fu, H., Gong, M., & Tao, D. (2019). Geometry-aware symmetric domain adaptation for monocular depth estimation. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 9788–9798).
Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2881–2890).
Zhao, C., Zhang, Y., Poggi, M., Tosi, F., Guo, X., Zhu, Z., Huang, G., Tang, Y., & Mattoccia, S. (2022). MonoViT: Self-supervised monocular depth estimation with a vision transformer. In 2022 international conference on 3D vision (3DV) (pp. 668–678). IEEE
Zhao, C., Sun, Q., Zhang, C., Tang, Y., & Qian, F. (2020). Monocular depth estimation based on deep learning: An overview. Science China Technological Sciences, 63(9), 1612–1627.
Zhao, C., Tang, Y., & Sun, Q. (2022). Unsupervised monocular depth estimation in highly complex environments. IEEE Transactions on Emerging Topics in Computational Intelligence, 6(5), 1237–1246.
Zheng, C., Cham, T. J., & Cai, J. (2018). T2Net: Synthetic-to-realistic translation for solving single-image depth estimation tasks. In European conference on computer vision (ECCV) (pp. 767–783).
Zhou, Z., & Dong, Q. (2022). Self-distilled feature aggregation for self-supervised monocular depth estimation. In European conference on computer vision (ECCV) (pp. 709–726).
Zhou, T., Brown, M., Snavely, N., & Lowe, D. G. (2017) Unsupervised learning of depth and ego-motion from video. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1851–1858).
Acknowledgements
This research was supported in part by the National Natural Science Foundation of China (62271410) and the Fundamental Research Funds for the Central Universities.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Oliver Zendel.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xiang, M., Dai, Y., Zhang, F. et al. Towards a Unified Network for Robust Monocular Depth Estimation: Network Architecture, Training Strategy and Dataset. Int J Comput Vis 132, 1012–1028 (2024). https://doi.org/10.1007/s11263-023-01915-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-023-01915-6