Realistic Blur Synthesis for Learning Image Deblurring
- Title
- Realistic Blur Synthesis for Learning Image Deblurring
- Authors
- RIM, JAESUNG; KIM, GEONUNG; KIM, JUNGEON; LEE, JUNYONG; LEE, SEUNGYONG; CHO, SUNGHYUN
- Date Issued
- 2022-10-26
- Publisher
- European Computer Vision Association
- Abstract
- © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Training learning-based deblurring methods demands a tre-mendous 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. To resolve this, this paper analyzes various factors that introduce differences between real and synthetic blurred images. To this end, we present RSBlur, a novel dataset with real blurred images and the corresponding sharp image sequences to enable a detailed analysis of the difference between real and synthetic blur. With the dataset, we reveal the effects of different factors in the blur generation process. Based on the analysis, we also present a novel blur synthesis pipeline to synthesize more realistic blur. We show that our synthesis pipeline can improve the deblurring performance on real blurred images.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/114435
- ISSN
- 0302-9743
- Article Type
- Conference
- Citation
- ECCV, page. 487 - 503, 2022-10-26
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.