Journal
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
Volume 31, Issue 8, Pages 2994-3009Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2020.3035664
Keywords
Cameras; Kernel; Feature extraction; Image restoration; Estimation; Learning systems; Image edge detection; Convolutional neural network; dynamic scene blind deblurring; multi-scale model; channel attention; spatial pyramid pooling
Categories
Funding
- National Natural Science Foundation of China [61601070, 61501074]
- Key Project of Science and Technology Research of Chongqing Education Commission [KJZD-K201800603]
- Major Project of Science and Technology Research of Chongqing Education Commission [KJZDM201900602]
- Foundation Research and Advanced Exploration Project of Chongqing [cstc2018jcyjAX0432]
- Special General Program of Technology Innovation and Application Development of Chongqing [cstc2020jscx-msxmX0135]
Ask authors/readers for more resources
The paper proposes a novel multi-scale channel attention network (MSCAN) for effective single image dynamic scene blind deblurring, combining a spatial pyramid pooling channel attention strategy for more powerful network representation. Extensive experiments show that the method outperforms state-of-the-art SIDSBD methods in both qualitative evaluation and quantitative metrics.
The success of convolutional neural network (CNN) based single image dynamic scene blind deblurring (SIDSBD) methods mainly stems from the multi-scale/multi-patch model and the designs of the encoder-decoder architecture, and the residual block structure, which make different contributions to SIDSBD. In this paper, we further exploit the advantages of the multi-scale model, the encoder-decoder module, and the residual block structure, respectively, and propose a novel multi-scale channel attention network (MSCAN) for effective single image dynamic scene blind deblurring. Different from existing multi-scale models, in our proposed network, each scale consists of multiple levels, in which a novel spatial pyramid pooling channel attention (SPPCA) strategy is proposed to adaptively rescale the channel-wise features by using both the global and local feature statistics for more powerful network representation. Extensive experiments on both the synthetic benchmark datasets and the real blurred images show that our method can produce better deblurring results than the state-of-the-art SIDSBD methods in terms of both qualitative evaluation and quantitative metrics.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available