Abstract

Training learning-based deblurring methods demands a tremendous amount of blurred and sharp image pairs. Unfortunately, existing synthetic datasets are not realistic enough, and deblurring models trained on them cannot handle real blurred images effectively. While real datasets have recently been proposed, they provide limited diversity of scenes and camera settings, and capturing real datasets for diverse settings is still challenging. This paper present RSBlur, a novel dataset with real blurred images and the corresponding sharp image sequences to enable a detailed analysis of the differences between real and synthetic blur. With the RSBlur dataset, we analyzes various factors that introduce differences between real and synthetic blurred images, and presents a novel blur synthesis pipeline to synthesize more realistic blur. We also show that the effects of different factors in blur synthesis and our synthesis method can improve the deblurring performance on real blurred images.

Results