UEOF

Authors

• Nick Truong, University of Texas at Arlington
• Pritam P. Karkomar, University of Texas at Arlington
• William J. Beksi, University of Texas at Arlington

ORCID Identifier(s)

ORCID 0009-0003-6467-1014, ORCID 0000-0003-4578-6767, ORCID 0000-0001-5377-2627

Document Type

Dataset

DOI

https://doi.org/10.32855/dataset.2026.02.045

Depositor

William J. Beksi

Deposit Date

2-19-2026

Abstract

UEOF is the first synthetic underwater event-based optical flow dataset derived from physically-based ray-traced RGBD sequences. It was constructed using a modern video-to-event pipeline applied to rendered underwater videos. It consists of realistic event data streams with dense ground-truth flow, depth, and camera motion. The dataset is composed of 12 minutes and 51 seconds of data across 13,714 RGB frames. This results in a total of 4.94 billion events across all scenes. UEOF exhibits a high dynamic range of motion with a mean flow magnitude of 6.1 px and a median of 3.6 px. The motion distribution is heavy-tailed. While a majority of pixels undergo moderate displacement (with a 95th percentile of 21.20 px), the dataset also includes significant high-magnitude flow upwards of 80 px.

Disciplines

Artificial Intelligence and Robotics

Publication Date

Spring 2-19-2026

Comments

Project website: https://robotic-vision-lab.github.io/ueof

License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Recommended Citation

@data{mavmatrix/dataset.2026.02.045, title={{UEOF}}, author={Truong, Nick and Karmokar, Pritam P and Beksi, William J}, publisher={MavMatrix}, version={V1}, url={https://doi.org/10.32855/dataset.2026.02.045}, doi={10.32855/dataset.2026.02.045}, year={2026}}