Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197977908> ?p ?o ?g. }
- W3197977908 endingPage "376" @default.
- W3197977908 startingPage "376" @default.
- W3197977908 abstract "Recent studies on image restoration (IR) methods under unrolled optimization frameworks have shown that deep convolutional neural networks (DCNNs) can be implicitly used as priors to solve inverse problems. Due to the ill-conditioned nature of the inverse problem, the selection of prior knowledge is crucial for the process of IR. However, the existing methods use a fixed DCNN in each iteration, and so they cannot fully adapt to the image characteristics at each iteration stage. In this paper, we combine deep learning with traditional optimization and propose an end-to-end unrolled network based on deep priors. The entire network contains several iterations, and each iteration is composed of analytic solution updates and a small multiscale deep denoiser network. In particular, we use different denoiser networks at different stages to improve adaptability. Compared with a fixed DCNN, it greatly reduces the number of computations when the total parameters are equal and the number of iterations is the same, but the gains from a practical runtime are not as significant as indicated in the FLOP count. The experimental results of our method of three IR tasks, including denoising, deblurring, and lensless imaging, demonstrate that our proposed method achieves state-of-the-art performances in terms of both visual effects and quantitative evaluations." @default.
- W3197977908 created "2021-09-13" @default.
- W3197977908 creator A5003982996 @default.
- W3197977908 creator A5037892678 @default.
- W3197977908 creator A5049489926 @default.
- W3197977908 date "2021-09-08" @default.
- W3197977908 modified "2023-09-26" @default.
- W3197977908 title "Image Restoration Based on End-to-End Unrolled Network" @default.
- W3197977908 cites W1885185971 @default.
- W3197977908 cites W1906770428 @default.
- W3197977908 cites W1958968158 @default.
- W3197977908 cites W1978749115 @default.
- W3197977908 cites W2011181254 @default.
- W3197977908 cites W2014311222 @default.
- W3197977908 cites W2025900737 @default.
- W3197977908 cites W2028349405 @default.
- W3197977908 cites W2051834767 @default.
- W3197977908 cites W2056370875 @default.
- W3197977908 cites W2083609718 @default.
- W3197977908 cites W2100556411 @default.
- W3197977908 cites W2103972604 @default.
- W3197977908 cites W2114122776 @default.
- W3197977908 cites W2117539524 @default.
- W3197977908 cites W2119290843 @default.
- W3197977908 cites W2121058967 @default.
- W3197977908 cites W2130184048 @default.
- W3197977908 cites W2133665775 @default.
- W3197977908 cites W2146842127 @default.
- W3197977908 cites W2153663612 @default.
- W3197977908 cites W2160547390 @default.
- W3197977908 cites W2487564216 @default.
- W3197977908 cites W2508457857 @default.
- W3197977908 cites W2751646824 @default.
- W3197977908 cites W2765431787 @default.
- W3197977908 cites W2784344583 @default.
- W3197977908 cites W2905472194 @default.
- W3197977908 cites W2958407396 @default.
- W3197977908 cites W2963299521 @default.
- W3197977908 cites W2963814976 @default.
- W3197977908 cites W3000775737 @default.
- W3197977908 cites W3008334448 @default.
- W3197977908 cites W3049384743 @default.
- W3197977908 cites W3103393705 @default.
- W3197977908 cites W3104725225 @default.
- W3197977908 cites W3105425607 @default.
- W3197977908 cites W3123837026 @default.
- W3197977908 cites W3192151122 @default.
- W3197977908 doi "https://doi.org/10.3390/photonics8090376" @default.
- W3197977908 hasPublicationYear "2021" @default.
- W3197977908 type Work @default.
- W3197977908 sameAs 3197977908 @default.
- W3197977908 citedByCount "1" @default.
- W3197977908 countsByYear W31979779082023 @default.
- W3197977908 crossrefType "journal-article" @default.
- W3197977908 hasAuthorship W3197977908A5003982996 @default.
- W3197977908 hasAuthorship W3197977908A5037892678 @default.
- W3197977908 hasAuthorship W3197977908A5049489926 @default.
- W3197977908 hasBestOaLocation W31979779081 @default.
- W3197977908 hasConcept C106430172 @default.
- W3197977908 hasConcept C107673813 @default.
- W3197977908 hasConcept C108583219 @default.
- W3197977908 hasConcept C111919701 @default.
- W3197977908 hasConcept C11413529 @default.
- W3197977908 hasConcept C115961682 @default.
- W3197977908 hasConcept C126255220 @default.
- W3197977908 hasConcept C134306372 @default.
- W3197977908 hasConcept C135252773 @default.
- W3197977908 hasConcept C154945302 @default.
- W3197977908 hasConcept C177769412 @default.
- W3197977908 hasConcept C207467116 @default.
- W3197977908 hasConcept C2524010 @default.
- W3197977908 hasConcept C2777693668 @default.
- W3197977908 hasConcept C33923547 @default.
- W3197977908 hasConcept C41008148 @default.
- W3197977908 hasConcept C74296488 @default.
- W3197977908 hasConcept C81363708 @default.
- W3197977908 hasConcept C9417928 @default.
- W3197977908 hasConcept C98045186 @default.
- W3197977908 hasConceptScore W3197977908C106430172 @default.
- W3197977908 hasConceptScore W3197977908C107673813 @default.
- W3197977908 hasConceptScore W3197977908C108583219 @default.
- W3197977908 hasConceptScore W3197977908C111919701 @default.
- W3197977908 hasConceptScore W3197977908C11413529 @default.
- W3197977908 hasConceptScore W3197977908C115961682 @default.
- W3197977908 hasConceptScore W3197977908C126255220 @default.
- W3197977908 hasConceptScore W3197977908C134306372 @default.
- W3197977908 hasConceptScore W3197977908C135252773 @default.
- W3197977908 hasConceptScore W3197977908C154945302 @default.
- W3197977908 hasConceptScore W3197977908C177769412 @default.
- W3197977908 hasConceptScore W3197977908C207467116 @default.
- W3197977908 hasConceptScore W3197977908C2524010 @default.
- W3197977908 hasConceptScore W3197977908C2777693668 @default.
- W3197977908 hasConceptScore W3197977908C33923547 @default.
- W3197977908 hasConceptScore W3197977908C41008148 @default.
- W3197977908 hasConceptScore W3197977908C74296488 @default.
- W3197977908 hasConceptScore W3197977908C81363708 @default.
- W3197977908 hasConceptScore W3197977908C9417928 @default.
- W3197977908 hasConceptScore W3197977908C98045186 @default.