Accessibility navigation


The third monocular depth estimation challenge

Spencer, J., Tosi, F., Poggi, M., Singh Arora, R., Russell, C., Hadfield, S., Bowden, R., Zhou, G. Y., Zheng, X. L., Rao, Q., Bao, Y., Liu, X., Kim, D., Kim, J., Kim, M., Lavreniuk, M., Li, R., Mao, Q., Wu, J., Zhu, Y. , Sun, J., Zhang, Y., Patni, S., Agarwal, A., Arora, C., Sun, P., Jiang, K., Wu, G., Liu, J., Liu, X., Jiang, J., Zhang, X., Wei, J., Wang, F., Tan, Z., Wang, J., Luginov, A., Shahzad, M. ORCID: https://orcid.org/0009-0002-9394-343X, Hosseini, S., Trajcevski, A. and Elder, J. H. (2024) The third monocular depth estimation challenge. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024, 17-18 Jun 2024, Seatle, USA. (In Press)

[img] Text - Accepted Version
· Restricted to Repository staff only
· The Copyright of this document has not been checked yet. This may affect its availability.

12MB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

Official URL: https://arxiv.org/abs/2404.16831

Abstract/Summary

This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.

Item Type:Conference or Workshop Item (Paper)
Refereed:Yes
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:116215

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation