Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132693282> ?p ?o ?g. }
- W3132693282 endingPage "1" @default.
- W3132693282 startingPage "1" @default.
- W3132693282 abstract "Existing face hallucination methods based on convolutional neural networks (CNNs) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in non-uniform illumination conditions. This paper proposes a Recursive Copy and Paste Generative Adversarial Network (Re-CPGAN) to recover authentic high-resolution (HR) face images while compensating for non-uniform illumination. To this end, we develop two key components in our Re-CPGAN: internal and recursive external Copy and Paste networks (CPnets). Our internal CPnet exploits facial self-similarity information residing in the input image to enhance facial details; while our recursive external CPnet leverages an external guided face for illumination compensation. Specifically, our recursive external CPnet stacks multiple external Copy and Paste (EX-CP) units in a compact model to learn normal illumination and enhance facial details recursively. By doing so, our method offsets illumination and upsamples facial details progressively in a coarse-to-fine fashion, thus alleviating the ambiguity of correspondences between LR inputs and external guided inputs. Furthermore, a new illumination compensation loss is developed to capture illumination from the external guided face image effectively. Extensive experiments demonstrate that our method achieves authentic HR face images in a uniform illumination condition with a 16× magnification factor and outperforms state-of-the-art methods qualitatively and quantitatively." @default.
- W3132693282 created "2021-03-01" @default.
- W3132693282 creator A5003076238 @default.
- W3132693282 creator A5010961909 @default.
- W3132693282 creator A5021751767 @default.
- W3132693282 creator A5064763991 @default.
- W3132693282 creator A5066658319 @default.
- W3132693282 creator A5087244134 @default.
- W3132693282 date "2021-01-01" @default.
- W3132693282 modified "2023-10-14" @default.
- W3132693282 title "Recursive Copy and Paste GAN: Face Hallucination from Shaded Thumbnails" @default.
- W3132693282 cites W1506013575 @default.
- W3132693282 cites W1834627138 @default.
- W3132693282 cites W1913007689 @default.
- W3132693282 cites W1934184906 @default.
- W3132693282 cites W1969306251 @default.
- W3132693282 cites W1972002222 @default.
- W3132693282 cites W1999457380 @default.
- W3132693282 cites W2003749430 @default.
- W3132693282 cites W2027560260 @default.
- W3132693282 cites W2063718733 @default.
- W3132693282 cites W2077931794 @default.
- W3132693282 cites W2083192529 @default.
- W3132693282 cites W2086665547 @default.
- W3132693282 cites W2097039786 @default.
- W3132693282 cites W2108428911 @default.
- W3132693282 cites W2125879936 @default.
- W3132693282 cites W2131081720 @default.
- W3132693282 cites W2141631520 @default.
- W3132693282 cites W2214802144 @default.
- W3132693282 cites W2237250383 @default.
- W3132693282 cites W2307770531 @default.
- W3132693282 cites W2520930090 @default.
- W3132693282 cites W2560535660 @default.
- W3132693282 cites W2603777577 @default.
- W3132693282 cites W2604439412 @default.
- W3132693282 cites W2607170299 @default.
- W3132693282 cites W2611646129 @default.
- W3132693282 cites W2617561348 @default.
- W3132693282 cites W2772236815 @default.
- W3132693282 cites W2780624730 @default.
- W3132693282 cites W2790630725 @default.
- W3132693282 cites W2798691622 @default.
- W3132693282 cites W2866634454 @default.
- W3132693282 cites W2895542678 @default.
- W3132693282 cites W2911422169 @default.
- W3132693282 cites W2912990735 @default.
- W3132693282 cites W2914057590 @default.
- W3132693282 cites W2943314296 @default.
- W3132693282 cites W2962793481 @default.
- W3132693282 cites W2962925415 @default.
- W3132693282 cites W2963035013 @default.
- W3132693282 cites W2963091558 @default.
- W3132693282 cites W2963186101 @default.
- W3132693282 cites W2963390109 @default.
- W3132693282 cites W2963393566 @default.
- W3132693282 cites W2963466847 @default.
- W3132693282 cites W2963470893 @default.
- W3132693282 cites W2963566548 @default.
- W3132693282 cites W2963583792 @default.
- W3132693282 cites W2963676087 @default.
- W3132693282 cites W2964094607 @default.
- W3132693282 cites W2969985801 @default.
- W3132693282 cites W2988058144 @default.
- W3132693282 cites W2989855043 @default.
- W3132693282 cites W3034338913 @default.
- W3132693282 cites W3034352949 @default.
- W3132693282 cites W3035338890 @default.
- W3132693282 cites W3104324613 @default.
- W3132693282 cites W3104792420 @default.
- W3132693282 cites W3110182603 @default.
- W3132693282 cites W3114544597 @default.
- W3132693282 cites W4231726432 @default.
- W3132693282 doi "https://doi.org/10.1109/tpami.2021.3061312" @default.
- W3132693282 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33621168" @default.
- W3132693282 hasPublicationYear "2021" @default.
- W3132693282 type Work @default.
- W3132693282 sameAs 3132693282 @default.
- W3132693282 citedByCount "13" @default.
- W3132693282 countsByYear W31326932822021 @default.
- W3132693282 countsByYear W31326932822022 @default.
- W3132693282 countsByYear W31326932822023 @default.
- W3132693282 crossrefType "journal-article" @default.
- W3132693282 hasAuthorship W3132693282A5003076238 @default.
- W3132693282 hasAuthorship W3132693282A5010961909 @default.
- W3132693282 hasAuthorship W3132693282A5021751767 @default.
- W3132693282 hasAuthorship W3132693282A5064763991 @default.
- W3132693282 hasAuthorship W3132693282A5066658319 @default.
- W3132693282 hasAuthorship W3132693282A5087244134 @default.
- W3132693282 hasConcept C110384440 @default.
- W3132693282 hasConcept C11171543 @default.
- W3132693282 hasConcept C115961682 @default.
- W3132693282 hasConcept C144024400 @default.
- W3132693282 hasConcept C153180895 @default.
- W3132693282 hasConcept C154945302 @default.
- W3132693282 hasConcept C15744967 @default.
- W3132693282 hasConcept C2779304628 @default.
- W3132693282 hasConcept C2780023022 @default.