IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Abstract
This paper reviews the first NTIRE challenge on video deblurring (restoration of rich details and high frequency components from blurred video frames) with focus on the proposed solutions and results. A new REalistic and Di- verse Scenes dataset (REDS) was employed. The challenge was divided into 2 tracks. Track 1 employed dynamic mo- tion blurs while Track 2 had additional MPEG video com- pression artifacts. Each competition had 109 and 93 reg- istered participants. Total 13 teams competed in the final testing phase. They gauge the state-of-the-art in video de- blurring problem.