Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion Deblurring
Blur kernel (BK) estimation is the crucial technique to guarantee the success of blind image deblurring. In this paper, we propose a multi-regularization-constrained method to estimate an accurate BK from a single motion-blurred image. First, in order to generate sharp and reliable intermediate late...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8600319/ |
| _version_ | 1818415873039269888 |
|---|---|
| author | Shu Tang Wanpeng Zheng Xianzhong Xie Tao He Peng Yang Lei Luo Zhixing Li Yu Hu Hao Zhao |
| author_facet | Shu Tang Wanpeng Zheng Xianzhong Xie Tao He Peng Yang Lei Luo Zhixing Li Yu Hu Hao Zhao |
| author_sort | Shu Tang |
| collection | DOAJ |
| description | Blur kernel (BK) estimation is the crucial technique to guarantee the success of blind image deblurring. In this paper, we propose a multi-regularization-constrained method to estimate an accurate BK from a single motion-blurred image. First, in order to generate sharp and reliable intermediate latent results, we propose a model which combines the spatial scale, <inline-formula> <tex-math notation="LaTeX">${L} _{0}$ </tex-math></inline-formula> norm, and the dark channel prior. Second, in order to preserve the continuity and the sparsity, and to remove the flaw in the BK, a dual-constrained regularization model, which combines the <inline-formula> <tex-math notation="LaTeX">${L} _{0}$ </tex-math></inline-formula>-regularized intensity prior and the <inline-formula> <tex-math notation="LaTeX">${L} _{2}$ </tex-math></inline-formula>-regularized gradient prior, is proposed for accurate BK estimation. The proposed model can not only preserve the continuity and the sparsity of the BK very well but also can remove the flaw thoroughly. Finally, we propose an efficient optimization strategy which can solve the proposed model efficiently. Extensive experiments compared with the state-of-the-art methods demonstrate that our method estimates more accurate BKs and obtains higher quality deblurring images in terms of both subjective vision and quantitative metrics. |
| first_indexed | 2024-12-14T11:41:54Z |
| format | Article |
| id | doaj.art-2741bf612d90430daf0054fa25cc68df |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T11:41:54Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2741bf612d90430daf0054fa25cc68df2022-12-21T23:02:46ZengIEEEIEEE Access2169-35362019-01-0175296531110.1109/ACCESS.2018.28894668600319Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion DeblurringShu Tang0https://orcid.org/0000-0001-7517-7992Wanpeng Zheng1Xianzhong Xie2Tao He3Peng Yang4Lei Luo5https://orcid.org/0000-0002-7008-4276Zhixing Li6Yu Hu7Hao Zhao8Chongqing Key Laboratory of Computer Network and Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Computer Network and Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Computer Network and Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Computer Network and Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Computer Network and Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Computer Network and Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Computer Network and Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaThe Sixth Inspection Bureau, Chongqing Municipal Tax Service, State Administration of Taxation, Chongqing, ChinaChongqing Branch Office, China Mobile Group Design Institute Co., Ltd., Chongqing, ChinaBlur kernel (BK) estimation is the crucial technique to guarantee the success of blind image deblurring. In this paper, we propose a multi-regularization-constrained method to estimate an accurate BK from a single motion-blurred image. First, in order to generate sharp and reliable intermediate latent results, we propose a model which combines the spatial scale, <inline-formula> <tex-math notation="LaTeX">${L} _{0}$ </tex-math></inline-formula> norm, and the dark channel prior. Second, in order to preserve the continuity and the sparsity, and to remove the flaw in the BK, a dual-constrained regularization model, which combines the <inline-formula> <tex-math notation="LaTeX">${L} _{0}$ </tex-math></inline-formula>-regularized intensity prior and the <inline-formula> <tex-math notation="LaTeX">${L} _{2}$ </tex-math></inline-formula>-regularized gradient prior, is proposed for accurate BK estimation. The proposed model can not only preserve the continuity and the sparsity of the BK very well but also can remove the flaw thoroughly. Finally, we propose an efficient optimization strategy which can solve the proposed model efficiently. Extensive experiments compared with the state-of-the-art methods demonstrate that our method estimates more accurate BKs and obtains higher quality deblurring images in terms of both subjective vision and quantitative metrics.https://ieeexplore.ieee.org/document/8600319/Blind image deblurringblur kernelspatial scale<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₀-regularized intensity prior<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₂-regularized gradient prior |
| spellingShingle | Shu Tang Wanpeng Zheng Xianzhong Xie Tao He Peng Yang Lei Luo Zhixing Li Yu Hu Hao Zhao Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion Deblurring IEEE Access Blind image deblurring blur kernel spatial scale <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₀-regularized intensity prior <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₂-regularized gradient prior |
| title | Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion Deblurring |
| title_full | Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion Deblurring |
| title_fullStr | Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion Deblurring |
| title_full_unstemmed | Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion Deblurring |
| title_short | Multi-Regularization-Constrained Blur Kernel Estimation Method for Blind Motion Deblurring |
| title_sort | multi regularization constrained blur kernel estimation method for blind motion deblurring |
| topic | Blind image deblurring blur kernel spatial scale <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₀-regularized intensity prior <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₂-regularized gradient prior |
| url | https://ieeexplore.ieee.org/document/8600319/ |
| work_keys_str_mv | AT shutang multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT wanpengzheng multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT xianzhongxie multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT taohe multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT pengyang multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT leiluo multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT zhixingli multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT yuhu multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring AT haozhao multiregularizationconstrainedblurkernelestimationmethodforblindmotiondeblurring |