Publication
Title
The second monocular depth estimation challenge
Author
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 pre-trained 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.
Language
English
Source (book)
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 17-24 June, 2023, Vancouver, BC, Canada
Publication
IEEE , 2023
ISBN
979-83-503-0249-3
DOI
10.1109/CVPRW59228.2023.00308
Volume/pages
p. 3064-3076
Full text (Publisher's DOI)
Full text (open access)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Record
Identifier
Creation 11.01.2024
Last edited 12.01.2024
To cite this reference