Matches in SemOpenAlex for { <https://semopenalex.org/work/W3121661546> ?p ?o ?g. }
- W3121661546 endingPage "2349" @default.
- W3121661546 startingPage "2340" @default.
- W3121661546 abstract "Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a self-regularized perceptual loss fusion, and the attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. Our codes and pre-trained models are available at: https://github.com/VITA-Group/EnlightenGAN." @default.
- W3121661546 created "2021-02-01" @default.
- W3121661546 creator A5001404316 @default.
- W3121661546 creator A5026746295 @default.
- W3121661546 creator A5038815767 @default.
- W3121661546 creator A5045685496 @default.
- W3121661546 creator A5047385834 @default.
- W3121661546 creator A5048522863 @default.
- W3121661546 creator A5051364953 @default.
- W3121661546 creator A5060482766 @default.
- W3121661546 creator A5083958225 @default.
- W3121661546 date "2021-01-01" @default.
- W3121661546 modified "2023-10-09" @default.
- W3121661546 title "EnlightenGAN: Deep Light Enhancement Without Paired Supervision" @default.
- W3121661546 cites W1580436348 @default.
- W3121661546 cites W2013784666 @default.
- W3121661546 cites W2054814429 @default.
- W3121661546 cites W2055745001 @default.
- W3121661546 cites W2058333183 @default.
- W3121661546 cites W2076205488 @default.
- W3121661546 cites W2102166818 @default.
- W3121661546 cites W2146439264 @default.
- W3121661546 cites W2150721269 @default.
- W3121661546 cites W2242218935 @default.
- W3121661546 cites W2254039850 @default.
- W3121661546 cites W2468596194 @default.
- W3121661546 cites W2552164092 @default.
- W3121661546 cites W2566376500 @default.
- W3121661546 cites W2572730214 @default.
- W3121661546 cites W2593414223 @default.
- W3121661546 cites W2626739722 @default.
- W3121661546 cites W2735974062 @default.
- W3121661546 cites W2736611505 @default.
- W3121661546 cites W2779176852 @default.
- W3121661546 cites W2783573276 @default.
- W3121661546 cites W2788682721 @default.
- W3121661546 cites W2791710889 @default.
- W3121661546 cites W2798844427 @default.
- W3121661546 cites W2799265886 @default.
- W3121661546 cites W2883566908 @default.
- W3121661546 cites W2962793481 @default.
- W3121661546 cites W2962903125 @default.
- W3121661546 cites W2963228457 @default.
- W3121661546 cites W2963470893 @default.
- W3121661546 cites W2963766909 @default.
- W3121661546 cites W2963767194 @default.
- W3121661546 cites W2963800716 @default.
- W3121661546 cites W2963890275 @default.
- W3121661546 cites W2963928582 @default.
- W3121661546 cites W2964030969 @default.
- W3121661546 cites W2967584026 @default.
- W3121661546 cites W2982795046 @default.
- W3121661546 cites W2983541695 @default.
- W3121661546 cites W2989221291 @default.
- W3121661546 cites W3013338555 @default.
- W3121661546 cites W3043547428 @default.
- W3121661546 cites W3109637563 @default.
- W3121661546 cites W4242059867 @default.
- W3121661546 doi "https://doi.org/10.1109/tip.2021.3051462" @default.
- W3121661546 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33481709" @default.
- W3121661546 hasPublicationYear "2021" @default.
- W3121661546 type Work @default.
- W3121661546 sameAs 3121661546 @default.
- W3121661546 citedByCount "613" @default.
- W3121661546 countsByYear W31216615462019 @default.
- W3121661546 countsByYear W31216615462020 @default.
- W3121661546 countsByYear W31216615462021 @default.
- W3121661546 countsByYear W31216615462022 @default.
- W3121661546 countsByYear W31216615462023 @default.
- W3121661546 crossrefType "journal-article" @default.
- W3121661546 hasAuthorship W3121661546A5001404316 @default.
- W3121661546 hasAuthorship W3121661546A5026746295 @default.
- W3121661546 hasAuthorship W3121661546A5038815767 @default.
- W3121661546 hasAuthorship W3121661546A5045685496 @default.
- W3121661546 hasAuthorship W3121661546A5047385834 @default.
- W3121661546 hasAuthorship W3121661546A5048522863 @default.
- W3121661546 hasAuthorship W3121661546A5051364953 @default.
- W3121661546 hasAuthorship W3121661546A5060482766 @default.
- W3121661546 hasAuthorship W3121661546A5083958225 @default.
- W3121661546 hasBestOaLocation W31216615462 @default.
- W3121661546 hasConcept C105795698 @default.
- W3121661546 hasConcept C108583219 @default.
- W3121661546 hasConcept C115961682 @default.
- W3121661546 hasConcept C13280743 @default.
- W3121661546 hasConcept C146849305 @default.
- W3121661546 hasConcept C153180895 @default.
- W3121661546 hasConcept C154945302 @default.
- W3121661546 hasConcept C169760540 @default.
- W3121661546 hasConcept C185798385 @default.
- W3121661546 hasConcept C205649164 @default.
- W3121661546 hasConcept C26760741 @default.
- W3121661546 hasConcept C2779803651 @default.
- W3121661546 hasConcept C2780598303 @default.
- W3121661546 hasConcept C31972630 @default.
- W3121661546 hasConcept C33923547 @default.
- W3121661546 hasConcept C41008148 @default.
- W3121661546 hasConcept C69744172 @default.
- W3121661546 hasConcept C76155785 @default.