FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042876812> ?p ?o ?g. }

• W3042876812 abstract "Abstract This paper addresses the traditional issue of restoring a high-resolution (HR) facial image from a low-resolution (LR) counterpart. Current state-of-the-art super-resolution (SR) methods commonly adopt the convolutional neural networks to learn a non-linear complex mapping between paired LR and HR images. They discriminate local patterns expressed by the neighboring pixels along the planar directions but ignore the intrinsic 3D proximity including the depth map. As a special case of general images, the face has limited geometric variations, which we believe that the relevant depth map can be learned and used to guide the face SR task. Motivated by it, we design a network including two branches: one for auxiliary depth map estimation and the other for the main SR task. Adaptive geometric features are further learned from the depth map and used to modulate the mid-level features of the SR branch. The whole network is implemented in an end-to-end trainable manner under the extra supervision of depth map. The supervisory depth map is either a paired one from RGB-D scans or a reconstructed one by a 3D prior model of faces. The experiments demonstrate the effectiveness of the proposed method and achieve improved performance over the state of the arts." @default.
• W3042876812 created "2020-07-23" @default.
• W3042876812 creator A5005423288 @default.
• W3042876812 creator A5016446416 @default.
• W3042876812 creator A5043440896 @default.
• W3042876812 creator A5063253432 @default.
• W3042876812 creator A5068139663 @default.
• W3042876812 date "2020-07-17" @default.
• W3042876812 modified "2023-10-03" @default.
• W3042876812 title "Facial image super-resolution guided by adaptive geometric features" @default.
• W3042876812 cites W1600550542 @default.
• W3042876812 cites W1901129140 @default.
• W3042876812 cites W2054515210 @default.
• W3042876812 cites W2087642411 @default.
• W3042876812 cites W2126653386 @default.
• W3042876812 cites W2133665775 @default.
• W3042876812 cites W2137659841 @default.
• W3042876812 cites W2166468061 @default.
• W3042876812 cites W2180648442 @default.
• W3042876812 cites W2194775991 @default.
• W3042876812 cites W2201706299 @default.
• W3042876812 cites W2237250383 @default.
• W3042876812 cites W2242218935 @default.
• W3042876812 cites W2342658046 @default.
• W3042876812 cites W2507235960 @default.
• W3042876812 cites W2520331172 @default.
• W3042876812 cites W2604524889 @default.
• W3042876812 cites W2763314014 @default.
• W3042876812 cites W2768814045 @default.
• W3042876812 cites W2792147336 @default.
• W3042876812 cites W2793833596 @default.
• W3042876812 cites W2796461436 @default.
• W3042876812 cites W2801026638 @default.
• W3042876812 cites W2889217990 @default.
• W3042876812 cites W2891158090 @default.
• W3042876812 cites W2894677449 @default.
• W3042876812 cites W2895542678 @default.
• W3042876812 cites W2900063223 @default.
• W3042876812 cites W2900135567 @default.
• W3042876812 cites W2901502713 @default.
• W3042876812 cites W2911353037 @default.
• W3042876812 cites W2913998974 @default.
• W3042876812 cites W2916106301 @default.
• W3042876812 cites W2947376905 @default.
• W3042876812 cites W2952841512 @default.
• W3042876812 cites W2955625300 @default.
• W3042876812 cites W2962770929 @default.
• W3042876812 cites W2963089432 @default.
• W3042876812 cites W2963372104 @default.
• W3042876812 cites W2963470893 @default.
• W3042876812 cites W2963563681 @default.
• W3042876812 cites W2963583792 @default.
• W3042876812 cites W2963676087 @default.
• W3042876812 cites W2964101377 @default.
• W3042876812 cites W2979177436 @default.
• W3042876812 cites W2979715398 @default.
• W3042876812 cites W3099091830 @default.
• W3042876812 cites W54257720 @default.
• W3042876812 doi "https://doi.org/10.1186/s13638-020-01760-y" @default.
• W3042876812 hasPublicationYear "2020" @default.
• W3042876812 type Work @default.
• W3042876812 sameAs 3042876812 @default.
• W3042876812 citedByCount "5" @default.
• W3042876812 countsByYear W30428768122021 @default.
• W3042876812 countsByYear W30428768122022 @default.
• W3042876812 crossrefType "journal-article" @default.
• W3042876812 hasAuthorship W3042876812A5005423288 @default.
• W3042876812 hasAuthorship W3042876812A5016446416 @default.
• W3042876812 hasAuthorship W3042876812A5043440896 @default.
• W3042876812 hasAuthorship W3042876812A5063253432 @default.
• W3042876812 hasAuthorship W3042876812A5068139663 @default.
• W3042876812 hasBestOaLocation W30428768121 @default.
• W3042876812 hasConcept C115961682 @default.
• W3042876812 hasConcept C141268832 @default.
• W3042876812 hasConcept C144024400 @default.
• W3042876812 hasConcept C153180895 @default.
• W3042876812 hasConcept C154945302 @default.
• W3042876812 hasConcept C160633673 @default.
• W3042876812 hasConcept C162324750 @default.
• W3042876812 hasConcept C187736073 @default.
• W3042876812 hasConcept C2779304628 @default.
• W3042876812 hasConcept C2780451532 @default.
• W3042876812 hasConcept C31972630 @default.
• W3042876812 hasConcept C36289849 @default.
• W3042876812 hasConcept C41008148 @default.
• W3042876812 hasConcept C81363708 @default.
• W3042876812 hasConcept C82990744 @default.
• W3042876812 hasConceptScore W3042876812C115961682 @default.
• W3042876812 hasConceptScore W3042876812C141268832 @default.
• W3042876812 hasConceptScore W3042876812C144024400 @default.
• W3042876812 hasConceptScore W3042876812C153180895 @default.
• W3042876812 hasConceptScore W3042876812C154945302 @default.
• W3042876812 hasConceptScore W3042876812C160633673 @default.
• W3042876812 hasConceptScore W3042876812C162324750 @default.
• W3042876812 hasConceptScore W3042876812C187736073 @default.
• W3042876812 hasConceptScore W3042876812C2779304628 @default.
• W3042876812 hasConceptScore W3042876812C2780451532 @default.
• W3042876812 hasConceptScore W3042876812C31972630 @default.
• W3042876812 hasConceptScore W3042876812C36289849 @default.
• W3042876812 hasConceptScore W3042876812C41008148 @default.

• next