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).
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.
More information
Identifiers
Catalogue record
Export record
Altmetrics
Contributors
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.