FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172689673> ?p ?o ?g. }

• W3172689673 endingPage "5834" @default.
• W3172689673 startingPage "5819" @default.
• W3172689673 abstract "Recent works that utilized deep models have achieved superior results in various image restoration (IR) applications. Such approach is typically supervised, which requires a corpus of training images with distributions similar to the images to be recovered. On the other hand, the shallow methods, which are usually unsupervised remain promising performance in many inverse problems, e.g., image deblurring and image compressive sensing (CS), as they can effectively leverage nonlocal self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various artifacts due to naive patch aggregation in addition to the slow speed. Using either approach alone usually limits performance and generalizability in IR tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely, internal and external, shallow and deep, and non-local and local priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for IR. Following this, a simple yet effective algorithm is developed to solve the proposed H-PnP based IR problems. Extensive experimental results on several representative IR tasks, including image deblurring, image CS and image deblocking, demonstrate that the proposed H-PnP algorithm achieves favorable performance compared to many popular or state-of-the-art IR methods in terms of both objective and visual perception." @default.
• W3172689673 created "2021-06-22" @default.
• W3172689673 creator A5015431603 @default.
• W3172689673 creator A5024709593 @default.
• W3172689673 creator A5032774989 @default.
• W3172689673 creator A5034427070 @default.
• W3172689673 creator A5037979193 @default.
• W3172689673 creator A5045125183 @default.
• W3172689673 date "2021-01-01" @default.
• W3172689673 modified "2023-10-14" @default.
• W3172689673 title "Triply Complementary Priors for Image Restoration" @default.
• W3172689673 cites W1588663000 @default.
• W3172689673 cites W1885185971 @default.
• W3172689673 cites W1906770428 @default.
• W3172689673 cites W1969698720 @default.
• W3172689673 cites W1973567017 @default.
• W3172689673 cites W1978749115 @default.
• W3172689673 cites W1984077106 @default.
• W3172689673 cites W2002969407 @default.
• W3172689673 cites W2014311222 @default.
• W3172689673 cites W2026517977 @default.
• W3172689673 cites W2040895929 @default.
• W3172689673 cites W2045737896 @default.
• W3172689673 cites W2048695508 @default.
• W3172689673 cites W2056370875 @default.
• W3172689673 cites W2062565740 @default.
• W3172689673 cites W2075157914 @default.
• W3172689673 cites W2075861921 @default.
• W3172689673 cites W2087416986 @default.
• W3172689673 cites W2097073572 @default.
• W3172689673 cites W2110158442 @default.
• W3172689673 cites W2125527601 @default.
• W3172689673 cites W2133665775 @default.
• W3172689673 cites W2135065661 @default.
• W3172689673 cites W2142683286 @default.
• W3172689673 cites W2153663612 @default.
• W3172689673 cites W2168668658 @default.
• W3172689673 cites W2172275395 @default.
• W3172689673 cites W2273561594 @default.
• W3172689673 cites W2288002998 @default.
• W3172689673 cites W2293090580 @default.
• W3172689673 cites W2408480187 @default.
• W3172689673 cites W2423236762 @default.
• W3172689673 cites W2505029951 @default.
• W3172689673 cites W2536599074 @default.
• W3172689673 cites W2573726823 @default.
• W3172689673 cites W2613155248 @default.
• W3172689673 cites W2747865121 @default.
• W3172689673 cites W2779105280 @default.
• W3172689673 cites W2784344583 @default.
• W3172689673 cites W2798559986 @default.
• W3172689673 cites W2798735168 @default.
• W3172689673 cites W2883208648 @default.
• W3172689673 cites W2884144629 @default.
• W3172689673 cites W2884569173 @default.
• W3172689673 cites W2888395215 @default.
• W3172689673 cites W2889024474 @default.
• W3172689673 cites W2889700716 @default.
• W3172689673 cites W2889923760 @default.
• W3172689673 cites W2902402285 @default.
• W3172689673 cites W2902719825 @default.
• W3172689673 cites W2963081547 @default.
• W3172689673 cites W2963091558 @default.
• W3172689673 cites W2963299521 @default.
• W3172689673 cites W2963814976 @default.
• W3172689673 cites W2980149757 @default.
• W3172689673 cites W2983736948 @default.
• W3172689673 cites W2987869089 @default.
• W3172689673 cites W2995679912 @default.
• W3172689673 cites W2998391154 @default.
• W3172689673 cites W3000775737 @default.
• W3172689673 cites W3006196464 @default.
• W3172689673 cites W3009338239 @default.
• W3172689673 cites W3012002796 @default.
• W3172689673 cites W3012209675 @default.
• W3172689673 cites W3016410830 @default.
• W3172689673 cites W3035514855 @default.
• W3172689673 cites W3038886336 @default.
• W3172689673 cites W3081108418 @default.
• W3172689673 cites W3090249111 @default.
• W3172689673 cites W3102722370 @default.
• W3172689673 cites W3104725225 @default.
• W3172689673 cites W3105198140 @default.
• W3172689673 cites W3123837026 @default.
• W3172689673 cites W3161747711 @default.
• W3172689673 cites W4242059867 @default.
• W3172689673 doi "https://doi.org/10.1109/tip.2021.3086049" @default.
• W3172689673 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34133279" @default.
• W3172689673 hasPublicationYear "2021" @default.
• W3172689673 type Work @default.
• W3172689673 sameAs 3172689673 @default.
• W3172689673 citedByCount "32" @default.
• W3172689673 countsByYear W31726896732022 @default.
• W3172689673 countsByYear W31726896732023 @default.
• W3172689673 crossrefType "journal-article" @default.
• W3172689673 hasAuthorship W3172689673A5015431603 @default.
• W3172689673 hasAuthorship W3172689673A5024709593 @default.
• W3172689673 hasAuthorship W3172689673A5032774989 @default.

• next