The 5th UG2+ Workshop and Prize Challenge: Bridging the Gap between Computational Photography and Visual Recognition.
In conjunction with CVPR 2022, June 19

Website: http://www.ug2challenge.org/
Challenge Registration: https://forms.gle/Td6DQuAJuuoLptN58
CMT: https://cmt3.research.microsoft.com/UG2CHALLENGE2022
Contact: cvpr2022.ug2challenge@gmail.com

Track 1: Object Detection in Haze Conditions
A dependable vision system must reckon with the entire spectrum of complex unconstrained and dynamic degraded outdoor environments. It is highly desirable to study to what extent, and in what sense, such challenging visual conditions can be coped with, for the goal of achieving robust visual sensing. This challenge aims to evaluate and advance object detection algorithms’ robustness in haze condition.

Track 2: Action Recognition from Dark Videos
Videos shot under adverse illumination are unavoidable, such as night surveillance, and self-driving at night. It is therefore highly desirable to explore robust methods to cope with dark scenarios. It would be even better if such methods could utilize web videos, which are widely available and normally shot under poor illumination.  This challenge aims to promote action recognition algorithms’ robustness with special focus on dark videos.

Track 3: Action Recognition from Dark Videos
The theories of turbulence and propagation of light through random media have been studied for the better part of a century. However, under turbulence and propagation of light through random media, progress of modern image reconstruction algorithms (e.g., deep learning methods) has been slow. This challenge aims to promote the development of new image reconstruction algorithms for incoherent imaging through anisoplanatic turbulence.

Submission: https://cmt3.research.microsoft.com/UG2CHALLENGE2022