Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081639259> ?p ?o ?g. }
- W3081639259 abstract "Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinders its performance due to the lack of suitable denoiser prior. In order to push the limits of plug-and-play image restoration, we set up a benchmark deep denoiser prior by training a highly flexible and effective CNN denoiser. We then plug the deep denoiser prior as a modular part into a half quadratic splitting based iterative algorithm to solve various image restoration problems. We, meanwhile, provide a thorough analysis of parameter setting, intermediate results and empirical convergence to better understand the working mechanism. Experimental results on three representative image restoration tasks, including deblurring, super-resolution and demosaicing, demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state-of-the-art learning-based methods. The source code is available at this https URL." @default.
- W3081639259 created "2020-09-08" @default.
- W3081639259 creator A5001254143 @default.
- W3081639259 creator A5003850660 @default.
- W3081639259 creator A5018318136 @default.
- W3081639259 creator A5052236177 @default.
- W3081639259 creator A5074728263 @default.
- W3081639259 creator A5080798381 @default.
- W3081639259 date "2020-08-31" @default.
- W3081639259 modified "2023-10-18" @default.
- W3081639259 title "Plug-and-Play Image Restoration with Deep Denoiser Prior" @default.
- W3081639259 cites W1545988247 @default.
- W3081639259 cites W1663973292 @default.
- W3081639259 cites W1885185971 @default.
- W3081639259 cites W1892266664 @default.
- W3081639259 cites W1901129140 @default.
- W3081639259 cites W1906770428 @default.
- W3081639259 cites W1912194039 @default.
- W3081639259 cites W1996726072 @default.
- W3081639259 cites W2016598597 @default.
- W3081639259 cites W2021347102 @default.
- W3081639259 cites W2048695508 @default.
- W3081639259 cites W2051834767 @default.
- W3081639259 cites W2056370875 @default.
- W3081639259 cites W2092663520 @default.
- W3081639259 cites W2097073572 @default.
- W3081639259 cites W2113945798 @default.
- W3081639259 cites W2119290843 @default.
- W3081639259 cites W2121927366 @default.
- W3081639259 cites W2130184048 @default.
- W3081639259 cites W2130975789 @default.
- W3081639259 cites W2138204001 @default.
- W3081639259 cites W2142683286 @default.
- W3081639259 cites W2146782367 @default.
- W3081639259 cites W2151502878 @default.
- W3081639259 cites W2153663612 @default.
- W3081639259 cites W2164278908 @default.
- W3081639259 cites W2170608748 @default.
- W3081639259 cites W2171650716 @default.
- W3081639259 cites W2172275395 @default.
- W3081639259 cites W2194775991 @default.
- W3081639259 cites W2202027014 @default.
- W3081639259 cites W2263237637 @default.
- W3081639259 cites W2263468737 @default.
- W3081639259 cites W2379948024 @default.
- W3081639259 cites W2395103039 @default.
- W3081639259 cites W2410797836 @default.
- W3081639259 cites W2508457857 @default.
- W3081639259 cites W2556068545 @default.
- W3081639259 cites W2556872594 @default.
- W3081639259 cites W2573726823 @default.
- W3081639259 cites W2613155248 @default.
- W3081639259 cites W2741137940 @default.
- W3081639259 cites W2765431787 @default.
- W3081639259 cites W2774320778 @default.
- W3081639259 cites W2776500869 @default.
- W3081639259 cites W2784344583 @default.
- W3081639259 cites W2798427787 @default.
- W3081639259 cites W2798559986 @default.
- W3081639259 cites W2866634454 @default.
- W3081639259 cites W2893749619 @default.
- W3081639259 cites W2895121927 @default.
- W3081639259 cites W2898685680 @default.
- W3081639259 cites W2902857081 @default.
- W3081639259 cites W2905472194 @default.
- W3081639259 cites W2913535645 @default.
- W3081639259 cites W2920942347 @default.
- W3081639259 cites W2921595853 @default.
- W3081639259 cites W2945291039 @default.
- W3081639259 cites W2952323569 @default.
- W3081639259 cites W2954930822 @default.
- W3081639259 cites W2962737939 @default.
- W3081639259 cites W2962935103 @default.
- W3081639259 cites W2963299521 @default.
- W3081639259 cites W2963372104 @default.
- W3081639259 cites W2963610452 @default.
- W3081639259 cites W2963614749 @default.
- W3081639259 cites W2963676935 @default.
- W3081639259 cites W2963725279 @default.
- W3081639259 cites W2963814976 @default.
- W3081639259 cites W2964046397 @default.
- W3081639259 cites W2964121744 @default.
- W3081639259 cites W2964204553 @default.
- W3081639259 cites W2965217508 @default.
- W3081639259 cites W2970295501 @default.
- W3081639259 cites W2989193306 @default.
- W3081639259 cites W3034504121 @default.
- W3081639259 cites W3035302306 @default.
- W3081639259 cites W3035496815 @default.
- W3081639259 cites W3086960204 @default.
- W3081639259 cites W3100730608 @default.
- W3081639259 cites W3109737331 @default.
- W3081639259 hasPublicationYear "2020" @default.
- W3081639259 type Work @default.
- W3081639259 sameAs 3081639259 @default.
- W3081639259 citedByCount "4" @default.
- W3081639259 countsByYear W30816392592020 @default.
- W3081639259 countsByYear W30816392592021 @default.
- W3081639259 crossrefType "posted-content" @default.
- W3081639259 hasAuthorship W3081639259A5001254143 @default.