Images and videos captured under adverse weather conditions such as rain, fog, haze, and snow suffer from severe quality degradation. These degradations—including reduced contrast, color distortion, blur, and noise—significantly impair the performance of downstream computer vision systems including object detectors, segmentation models, and other perception algorithms.

UG²+ Track 1 focuses on image restoration under all-weather conditions. Participants are challenged to develop robust restoration and enhancement algorithms that can handle the full spectrum of real-world weather degradations. The goal is to improve image quality in a manner that enhances the performance of downstream vision tasks operating on the restored images.

Full competition details, dataset downloads, submission instructions, and evaluation guidelines are available on the official competition page on Codabench:

View Competition on Codabench

If you have any questions about this challenge track please feel free to email cvpr2026.ug2challenge@gmail.com