The fourth monocular depth estimation challenge

Obukhov, A., Poggi, M., Tosi, F., Arora, R. S., Spencer, J., Russell, C., Hadfield, S., Bowden, R., Wang, S., Ma, Z., Chen, W., Xu, B., Sun, F., Xie, D., Zhu, J., Lavreniuk, M., Guan, H., Wu, Q., Zeng, Y., Lu, C., Wang, H., Zhou, G., Zhang, H., Wang, J., Rao, Q., Wang, C., Liu, X., Lou, Z., Jiang, H., Chen, Y., Xu, R., Tan, M., Qin, Z., Mao, Y., Liu, J., Xu, J., Yang, Y., Zhao, W., Jiang, J., Liu, X., Zhao, M., Ming, A., Chen, W., Xue, F., Yu, M., Gao, S., Wang, X., Omotara, G., Farag, R., Demby’s, J., Tousi, S. M. A., DeSouza, G. N., Yang, T.-A., Nguyen, M.-Q., Tran, T.-P., Luginov, A. and Shahzad, M. ORCID: https://orcid.org/0009-0002-9394-343X (2025) The fourth monocular depth estimation challenge. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 13-15 Jun 2025, Nashville, USA. doi: 10.1109/CVPRW67362.2025.00615

Abstract/Summary

This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affineinvariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition’s best result, raising it from 22.58% to 23.05%.

Item Type	Conference or Workshop Item (Paper)
URI	https://centaur.reading.ac.uk/id/eprint/124878
Identification Number/DOI	10.1109/CVPRW67362.2025.00615
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
Download/View statistics	View download statistics for this item