Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200729904> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3200729904 abstract "Deep learning-based methods have achieved remarkable success in low-light image enhancement. However, in the absence of a large number of low/normal light image pairs, it is still a challenge to train the enhancement network with good generalization ability. In this paper, we propose a highly effective unsupervised network for low-light image enhancement (named RGNET). We divide the enhancement task into two stages, complete from coarse to precise. At the first stage, we roughly amplify the input image nonlinearly using an unsupervised network. At the second stage, we build a two-path network to restore image details, one is uesed for residual restoration and the other is used for contextual attention. With the combination of reconstruction and adversarial loss, our enhancement effects are more consistant and natural than other GAN-based methods. Both quantitative and qualitative experiments on challenging datasets demonstrate the advantages of our method in comparison with state-of-the-art methods." @default.
- W3200729904 created "2021-09-27" @default.
- W3200729904 creator A5022200431 @default.
- W3200729904 creator A5030517812 @default.
- W3200729904 creator A5073933231 @default.
- W3200729904 date "2021-07-18" @default.
- W3200729904 modified "2023-10-14" @default.
- W3200729904 title "RGNET: A Two-stage Low-light Image Enhancement Network Without Paired Supervision" @default.
- W3200729904 cites W1528144695 @default.
- W3200729904 cites W1986086122 @default.
- W3200729904 cites W2011260964 @default.
- W3200729904 cites W2038713671 @default.
- W3200729904 cites W2054814429 @default.
- W3200729904 cites W2076205488 @default.
- W3200729904 cites W2096963464 @default.
- W3200729904 cites W2102166818 @default.
- W3200729904 cites W2254039850 @default.
- W3200729904 cites W2412926690 @default.
- W3200729904 cites W2566376500 @default.
- W3200729904 cites W2783573276 @default.
- W3200729904 cites W2799265886 @default.
- W3200729904 cites W2948354154 @default.
- W3200729904 cites W2998131124 @default.
- W3200729904 cites W2999935620 @default.
- W3200729904 cites W3034242291 @default.
- W3200729904 cites W3034331889 @default.
- W3200729904 cites W3034347506 @default.
- W3200729904 cites W3034359211 @default.
- W3200729904 cites W3034539499 @default.
- W3200729904 cites W3035002246 @default.
- W3200729904 cites W3035229960 @default.
- W3200729904 cites W3035631962 @default.
- W3200729904 cites W3035731588 @default.
- W3200729904 doi "https://doi.org/10.1109/ijcnn52387.2021.9533511" @default.
- W3200729904 hasPublicationYear "2021" @default.
- W3200729904 type Work @default.
- W3200729904 sameAs 3200729904 @default.
- W3200729904 citedByCount "1" @default.
- W3200729904 countsByYear W32007299042023 @default.
- W3200729904 crossrefType "proceedings-article" @default.
- W3200729904 hasAuthorship W3200729904A5022200431 @default.
- W3200729904 hasAuthorship W3200729904A5030517812 @default.
- W3200729904 hasAuthorship W3200729904A5073933231 @default.
- W3200729904 hasConcept C11413529 @default.
- W3200729904 hasConcept C115961682 @default.
- W3200729904 hasConcept C134306372 @default.
- W3200729904 hasConcept C153180895 @default.
- W3200729904 hasConcept C154945302 @default.
- W3200729904 hasConcept C155512373 @default.
- W3200729904 hasConcept C162324750 @default.
- W3200729904 hasConcept C177148314 @default.
- W3200729904 hasConcept C187736073 @default.
- W3200729904 hasConcept C2780451532 @default.
- W3200729904 hasConcept C3017601658 @default.
- W3200729904 hasConcept C31972630 @default.
- W3200729904 hasConcept C33923547 @default.
- W3200729904 hasConcept C41008148 @default.
- W3200729904 hasConceptScore W3200729904C11413529 @default.
- W3200729904 hasConceptScore W3200729904C115961682 @default.
- W3200729904 hasConceptScore W3200729904C134306372 @default.
- W3200729904 hasConceptScore W3200729904C153180895 @default.
- W3200729904 hasConceptScore W3200729904C154945302 @default.
- W3200729904 hasConceptScore W3200729904C155512373 @default.
- W3200729904 hasConceptScore W3200729904C162324750 @default.
- W3200729904 hasConceptScore W3200729904C177148314 @default.
- W3200729904 hasConceptScore W3200729904C187736073 @default.
- W3200729904 hasConceptScore W3200729904C2780451532 @default.
- W3200729904 hasConceptScore W3200729904C3017601658 @default.
- W3200729904 hasConceptScore W3200729904C31972630 @default.
- W3200729904 hasConceptScore W3200729904C33923547 @default.
- W3200729904 hasConceptScore W3200729904C41008148 @default.
- W3200729904 hasLocation W32007299041 @default.
- W3200729904 hasOpenAccess W3200729904 @default.
- W3200729904 hasPrimaryLocation W32007299041 @default.
- W3200729904 hasRelatedWork W2005185696 @default.
- W3200729904 hasRelatedWork W2161229648 @default.
- W3200729904 hasRelatedWork W2235753890 @default.
- W3200729904 hasRelatedWork W2909133588 @default.
- W3200729904 hasRelatedWork W2972435282 @default.
- W3200729904 hasRelatedWork W2993674027 @default.
- W3200729904 hasRelatedWork W3003805155 @default.
- W3200729904 hasRelatedWork W3123424645 @default.
- W3200729904 hasRelatedWork W4285786467 @default.
- W3200729904 hasRelatedWork W4293138881 @default.
- W3200729904 isParatext "false" @default.
- W3200729904 isRetracted "false" @default.
- W3200729904 magId "3200729904" @default.
- W3200729904 workType "article" @default.