Deep Recurrent Network for Fast and Full-Resolution Light Field Deblurring
- Title
- Deep Recurrent Network for Fast and Full-Resolution Light Field Deblurring
- Author
- 김태현
- Keywords
- Recurrent network; light field image; blind deblurring; dataset; 6-DOF motion
- Issue Date
- 2019-12
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Citation
- IEEE SIGNAL PROCESSING LETTERS, v. 26, no. 12, Page. 1788-1792
- Abstract
- The popularity of parallax-based image processing is increasing while in contrast early works on recovering sharp light field from its blurry input (deblurring) remain stagnant. State-of-the-art blind light field deblurring methods suffer from several problems such as slow processing, reduced spatial size, and simplified motion blur model. In this paper, we solve these challenging problems by proposing a novel light field recurrent deblurring network that is trained under 6 degree-of-freedom camera motion-blur model. By combining the real light field captured using Lytro Illum and synthetic light field rendering of 3D scenes from UnrealCV, we provide a large-scale blurry light field dataset to train the network. The proposed method outperforms the state-of-the-art methods in terms of deblurring quality, the capability of handling full-resolution, and a fast runtime.
- URI
- https://ieeexplore.ieee.org/document/8868185https://repository.hanyang.ac.kr/handle/20.500.11754/154513
- ISSN
- 1070-9908; 1558-2361
- DOI
- 10.1109/LSP.2019.2947379
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML