MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
- Title
- MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
- Authors
- KIM, KIYEON; LEE, SEUNGYONG; CHO, SUNGHYUN
- Date Issued
- 2022-10-24
- Publisher
- European Computer Vision Association
- Abstract
- Most traditional single image deblurring methods before deep learning adopt a coarse-to-fine scheme that estimates a sharp image at a coarse scale and progressively refines it at finer scales. While this scheme has also been adopted in several deep learning-based approaches, recently a number of single-scale approaches have been introduced showing superior performance to previous coarse-to-fine approaches in terms of quality and computation time. In this paper, we revisit the coarse-to-fine scheme and analyze the defects of previous coarse-to-fine approaches. Based on the analysis, we propose Multi-Scale-Stage Network (MSSNet), a novel deep learning-based approach to single image deblurring with our remedies to the defects. MSSNet adopts three remedies: stage configuration reflecting blur scales, an inter-scale information propagation scheme, and a pixel-shuffle-based multi-scale scheme. Our experiments show that our remedies can effectively resolve the defects of previous coarse-to-fine approaches and improve the deblurring performance.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/114436
- ISSN
- 0302-9743
- Article Type
- Conference
- Citation
- ECCV Workshop, page. 524 - 539, 2022-10-24
- 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.