Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166469601> ?p ?o ?g. }
- W3166469601 abstract "Plug-and-play prirs (PnP) is an image reconstruction framework that uses an image denoiser as an imaging prior. Unlike traditional regularized inversion, PnP does not require the prior to be expressible in the form of a regularization function. This flexibility enables PnP algorithms to exploit the most effective image denoisers, leading to their state-of-the-art performance in various imaging tasks. However, many powerful denoisers, such as the ones based on convolutional neural networks (CNNs), do not have tunable parameters that would allow controlling their influence within PnP. To address this issue, in this paper, we introduce a scaling parameter that adjusts the magnitude of the denoiser input and output. We theoretical justify the denoiser scaling from the perspectives of proximal optimization, statistical estimation, and consensus equilibrium. Finally, we provide numerical experiments demonstrating the ability of denoiser scaling to systematically improve the performance of PnP for denoising CNN priors that do not have explicitly tunable parameters." @default.
- W3166469601 created "2021-06-22" @default.
- W3166469601 creator A5015244709 @default.
- W3166469601 creator A5024602237 @default.
- W3166469601 creator A5069415047 @default.
- W3166469601 creator A5076370858 @default.
- W3166469601 creator A5084875333 @default.
- W3166469601 date "2020-11-01" @default.
- W3166469601 modified "2023-10-18" @default.
- W3166469601 title "Boosting the Performance of Plug-and-Play Priors via Denoiser Scaling" @default.
- W3166469601 cites W1906770428 @default.
- W3166469601 cites W1965875863 @default.
- W3166469601 cites W1987895141 @default.
- W3166469601 cites W1991217933 @default.
- W3166469601 cites W2047710600 @default.
- W3166469601 cites W2056370875 @default.
- W3166469601 cites W2058532290 @default.
- W3166469601 cites W2063650998 @default.
- W3166469601 cites W2087416986 @default.
- W3166469601 cites W2087572827 @default.
- W3166469601 cites W2100556411 @default.
- W3166469601 cites W2100705753 @default.
- W3166469601 cites W2103559027 @default.
- W3166469601 cites W2110505738 @default.
- W3166469601 cites W2115706991 @default.
- W3166469601 cites W2142224912 @default.
- W3166469601 cites W2153663612 @default.
- W3166469601 cites W2156706175 @default.
- W3166469601 cites W2190662802 @default.
- W3166469601 cites W2293327468 @default.
- W3166469601 cites W2508457857 @default.
- W3166469601 cites W2554591675 @default.
- W3166469601 cites W2556068545 @default.
- W3166469601 cites W2573726823 @default.
- W3166469601 cites W2613155248 @default.
- W3166469601 cites W2620976957 @default.
- W3166469601 cites W2763081248 @default.
- W3166469601 cites W2765431787 @default.
- W3166469601 cites W2889700716 @default.
- W3166469601 cites W2889923760 @default.
- W3166469601 cites W2963299521 @default.
- W3166469601 cites W2963426457 @default.
- W3166469601 cites W2963814976 @default.
- W3166469601 cites W2964215687 @default.
- W3166469601 cites W3003650457 @default.
- W3166469601 cites W3099887894 @default.
- W3166469601 cites W3101311698 @default.
- W3166469601 cites W3102025760 @default.
- W3166469601 cites W3105425607 @default.
- W3166469601 cites W3123837026 @default.
- W3166469601 cites W4244393449 @default.
- W3166469601 cites W4292363360 @default.
- W3166469601 doi "https://doi.org/10.1109/ieeeconf51394.2020.9443410" @default.
- W3166469601 hasPublicationYear "2020" @default.
- W3166469601 type Work @default.
- W3166469601 sameAs 3166469601 @default.
- W3166469601 citedByCount "14" @default.
- W3166469601 countsByYear W31664696012020 @default.
- W3166469601 countsByYear W31664696012021 @default.
- W3166469601 countsByYear W31664696012022 @default.
- W3166469601 countsByYear W31664696012023 @default.
- W3166469601 crossrefType "proceedings-article" @default.
- W3166469601 hasAuthorship W3166469601A5015244709 @default.
- W3166469601 hasAuthorship W3166469601A5024602237 @default.
- W3166469601 hasAuthorship W3166469601A5069415047 @default.
- W3166469601 hasAuthorship W3166469601A5076370858 @default.
- W3166469601 hasAuthorship W3166469601A5084875333 @default.
- W3166469601 hasBestOaLocation W31664696013 @default.
- W3166469601 hasConcept C107673813 @default.
- W3166469601 hasConcept C11413529 @default.
- W3166469601 hasConcept C153180895 @default.
- W3166469601 hasConcept C154945302 @default.
- W3166469601 hasConcept C177769412 @default.
- W3166469601 hasConcept C2524010 @default.
- W3166469601 hasConcept C2776135515 @default.
- W3166469601 hasConcept C33923547 @default.
- W3166469601 hasConcept C41008148 @default.
- W3166469601 hasConcept C46686674 @default.
- W3166469601 hasConcept C81363708 @default.
- W3166469601 hasConcept C99844830 @default.
- W3166469601 hasConceptScore W3166469601C107673813 @default.
- W3166469601 hasConceptScore W3166469601C11413529 @default.
- W3166469601 hasConceptScore W3166469601C153180895 @default.
- W3166469601 hasConceptScore W3166469601C154945302 @default.
- W3166469601 hasConceptScore W3166469601C177769412 @default.
- W3166469601 hasConceptScore W3166469601C2524010 @default.
- W3166469601 hasConceptScore W3166469601C2776135515 @default.
- W3166469601 hasConceptScore W3166469601C33923547 @default.
- W3166469601 hasConceptScore W3166469601C41008148 @default.
- W3166469601 hasConceptScore W3166469601C46686674 @default.
- W3166469601 hasConceptScore W3166469601C81363708 @default.
- W3166469601 hasConceptScore W3166469601C99844830 @default.
- W3166469601 hasFunder F4320337547 @default.
- W3166469601 hasLocation W31664696011 @default.
- W3166469601 hasLocation W31664696012 @default.
- W3166469601 hasLocation W31664696013 @default.
- W3166469601 hasOpenAccess W3166469601 @default.
- W3166469601 hasPrimaryLocation W31664696011 @default.
- W3166469601 hasRelatedWork W2003125512 @default.
- W3166469601 hasRelatedWork W2340694410 @default.