Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes
SCIE
SCOPUS
- Title
- Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes
- Authors
- SEUNGYONG LEE; SUNGHYUN CHO; HYEONGSEOK SON; JUNYONG LEE; JONGHYEOP LEE
- Date Issued
- 2021-10
- Publisher
- Association for Computing Machinary, Inc.
- Abstract
- For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation between video frames to aggregate information from multiple frames that can help deblur a target frame. However, the motion compensation methods adopted by previous deblurring methods are not blur-invariant, and consequently, their accuracy is limited for blurry frames with different blur amounts. To alleviate this problem, we propose two novel approaches to deblur videos by effectively aggregating information from multiple video frames. First, we present blur-invariant motion estimation learning to improvemotion estimation accuracy between blurry frames. Second, formotion compensation, instead of aligning frames by warping with estimated motions, we use a pixel volume that contains candidate sharp pixels to resolve motion estimation errors. We combine these two processes to propose an effective recurrent video deblurring network that fully exploits deblurred previous frames. Experiments show that our method achieves the state-of-the-art performance both quantitatively and qualitatively compared to recent methods that use deep learning.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/109384
- DOI
- 10.1145/3453720
- ISSN
- 0730-0301
- Article Type
- Article
- Citation
- ACM Transactions on Graphics, vol. 40, no. 5, 2021-10
- 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.