The University of Southampton
University of Southampton Institutional Repository

The second monocular depth estimation challenge: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

The second monocular depth estimation challenge: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
The second monocular depth estimation challenge: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC). This edition was open to methods using any form of supervision, including fully-supervised, self-supervised, multi-task or proxy depth. The challenge was based around the SYNS-Patches dataset, which features a wide diversity of environments with high-quality dense ground-truth. This includes complex natural environments, e.g. forests or fields, which are greatly underrepresented in current benchmarks.
The challenge received eight unique submissions that outperformed the provided SotA baseline on any of the pointcloud- or image-based metrics. The top supervised submission improved relative F-Score by 27.62%, while the top self-supervised improved it by 16.61%. Supervised submissions generally leveraged large collections of datasets to improve data diversity. Self-supervised submissions instead updated the network architecture and pretrained backbones. These results represent a significant progress in the field, while highlighting avenues for future research, such as reducing interpolation artifacts at depth boundaries, improving self-supervised indoor performance and overall natural image accuracy.
3064-3076
Qian, C. S.
b2a67035-30d1-475e-9e0b-572a0e6a5ed1
Trescakova, M.
509b9cd2-ae4d-4881-a484-22cb91e8af4c
Russell, C.
4df9e836-a84e-4eaf-8ea4-81724659c041
Hadfield, S.
94147f74-92b0-4904-ac22-e1b93c032188
Graf, E. W.
1a5123e2-8f05-4084-a6e6-837dcfc66209
Adams, W. J.
25685aaa-fc54-4d25-8d65-f35f4c5ab688
Elder, J.
b2ae1ed7-6081-4e4d-9818-b8db753d0531
Cheng, K.
f4eff3bf-c241-4c50-97a2-8c8b75cbec58
Hoa, H. T.
f3701c73-b5e5-4584-aba0-85548141f21f
Jing, M.
459afde7-02c1-4f33-9d70-d645fdf2f8e2
Mattoccia, S.
7e573b49-02aa-498a-8aff-ca06be1143b5
Mercelis, S.
f5333e1e-4e0e-4c8e-a664-e9b70e14908b
Nam, M.
5fe22355-bbe0-4a0e-b4e0-642d956c8ddb
Poggi, M.
e2ce847b-1b73-401d-8e0d-349112cd41ce
Tosi, F.
2d43db50-1f64-47ea-b410-d552b945d477
Trinh, L.
ff6de7ce-4f82-431e-b7d5-4c7fab6e923a
Uddin, S. M. N.
c1d00f12-ff56-443c-97fa-5a5024e32cbc
Umair, K. M.
072b4bd4-a00f-4cca-8de2-8d796bef6173
Xiang, M.
d313fbb7-521b-4254-aa89-62f5f043bd57
Xu, G.
7c42f7d2-67fb-4c7e-92c9-63281a339c65
Yu, J.
f0cc5bca-6305-4361-9b00-67975b8a1d2e
Qian, C. S.
b2a67035-30d1-475e-9e0b-572a0e6a5ed1
Trescakova, M.
509b9cd2-ae4d-4881-a484-22cb91e8af4c
Russell, C.
4df9e836-a84e-4eaf-8ea4-81724659c041
Hadfield, S.
94147f74-92b0-4904-ac22-e1b93c032188
Graf, E. W.
1a5123e2-8f05-4084-a6e6-837dcfc66209
Adams, W. J.
25685aaa-fc54-4d25-8d65-f35f4c5ab688
Elder, J.
b2ae1ed7-6081-4e4d-9818-b8db753d0531
Cheng, K.
f4eff3bf-c241-4c50-97a2-8c8b75cbec58
Hoa, H. T.
f3701c73-b5e5-4584-aba0-85548141f21f
Jing, M.
459afde7-02c1-4f33-9d70-d645fdf2f8e2
Mattoccia, S.
7e573b49-02aa-498a-8aff-ca06be1143b5
Mercelis, S.
f5333e1e-4e0e-4c8e-a664-e9b70e14908b
Nam, M.
5fe22355-bbe0-4a0e-b4e0-642d956c8ddb
Poggi, M.
e2ce847b-1b73-401d-8e0d-349112cd41ce
Tosi, F.
2d43db50-1f64-47ea-b410-d552b945d477
Trinh, L.
ff6de7ce-4f82-431e-b7d5-4c7fab6e923a
Uddin, S. M. N.
c1d00f12-ff56-443c-97fa-5a5024e32cbc
Umair, K. M.
072b4bd4-a00f-4cca-8de2-8d796bef6173
Xiang, M.
d313fbb7-521b-4254-aa89-62f5f043bd57
Xu, G.
7c42f7d2-67fb-4c7e-92c9-63281a339c65
Yu, J.
f0cc5bca-6305-4361-9b00-67975b8a1d2e

Qian, C. S., Trescakova, M., Russell, C., Hadfield, S., Graf, E. W., Adams, W. J., Elder, J., Cheng, K., Hoa, H. T., Jing, M., Mattoccia, S., Mercelis, S., Nam, M., Poggi, M., Tosi, F., Trinh, L., Uddin, S. M. N., Umair, K. M., Xiang, M., Xu, G. and Yu, J. (2023) The second monocular depth estimation challenge: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 17 - 24 Jun 2023. pp. 3064-3076 . (doi:10.48550/arXiv.2304.07051).

Record type: Conference or Workshop Item (Paper)

Abstract

This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC). This edition was open to methods using any form of supervision, including fully-supervised, self-supervised, multi-task or proxy depth. The challenge was based around the SYNS-Patches dataset, which features a wide diversity of environments with high-quality dense ground-truth. This includes complex natural environments, e.g. forests or fields, which are greatly underrepresented in current benchmarks.
The challenge received eight unique submissions that outperformed the provided SotA baseline on any of the pointcloud- or image-based metrics. The top supervised submission improved relative F-Score by 27.62%, while the top self-supervised improved it by 16.61%. Supervised submissions generally leveraged large collections of datasets to improve data diversity. Self-supervised submissions instead updated the network architecture and pretrained backbones. These results represent a significant progress in the field, while highlighting avenues for future research, such as reducing interpolation artifacts at depth boundaries, improving self-supervised indoor performance and overall natural image accuracy.

Other
ecfcc3ec-f36a-48ac-ac2f-cee08606e12f - Other
Available under License Creative Commons Attribution Share Alike.
Download (7MB)

More information

e-pub ahead of print date: 17 June 2023
Published date: 17 June 2023
Venue - Dates: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023-06-17 - 2023-06-24

Identifiers

Local EPrints ID: 481380
URI: http://eprints.soton.ac.uk/id/eprint/481380
PURE UUID: 7fca3a1e-148c-4fe7-bffc-94ca6f21aa89
ORCID for E. W. Graf: ORCID iD orcid.org/0000-0002-3162-4233
ORCID for W. J. Adams: ORCID iD orcid.org/0000-0002-5832-1056

Catalogue record

Date deposited: 24 Aug 2023 16:55
Last modified: 18 Mar 2024 02:59

Export record

Altmetrics

Contributors

Author: C. S. Qian
Author: M. Trescakova
Author: C. Russell
Author: S. Hadfield
Author: E. W. Graf ORCID iD
Author: W. J. Adams ORCID iD
Author: J. Elder
Author: K. Cheng
Author: H. T. Hoa
Author: M. Jing
Author: S. Mattoccia
Author: S. Mercelis
Author: M. Nam
Author: M. Poggi
Author: F. Tosi
Author: L. Trinh
Author: S. M. N. Uddin
Author: K. M. Umair
Author: M. Xiang
Author: G. Xu
Author: J. Yu

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×