Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176255692> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3176255692 endingPage "91174" @default.
- W3176255692 startingPage "91160" @default.
- W3176255692 abstract "This paper presents a novel model family that we call SUPERVEGAN, for the problem of video enhancement for low bitrate streams by simultaneous video super resolution and removal of compression artifacts from low bitrates (e.g. 250Kbps). Our strategy is fully end-to-end, but we upsample and tackle the problem in two main stages. The first stage deals with removal of streaming compression artifacts and performs a partial upsampling, and the second stage performs the final upsampling and adds detail generatively. We also use a novel progressive training strategy for video together with the use of perceptual metrics. Our experiments shown resilience to training bitrate and we show how to derive real-time models. We also introduce a novel bitrate equivalency test that enables the assessment of how much a model improves streams with respect to bitrate. We demonstrate efficacy on two publicly available HD datasets, LIVE-NFLX-II and Tears of Steel (TOS). We compare against a range of baselines and encoders and our results demonstrate our models achieve a perceptual equivalence which is up to two times over the input bitrate. In particular our 4X upsampling outperforms baseline methods on the LPIPS perceptual metric, and our 2X upsampling model also outperforms baselines on traditional metrics such as PSNR." @default.
- W3176255692 created "2021-07-05" @default.
- W3176255692 creator A5009469552 @default.
- W3176255692 creator A5044824896 @default.
- W3176255692 creator A5045779735 @default.
- W3176255692 date "2021-01-01" @default.
- W3176255692 modified "2023-09-26" @default.
- W3176255692 title "SUPERVEGAN: Super Resolution Video Enhancement GAN for Perceptually Improving Low Bitrate Streams" @default.
- W3176255692 cites W1576660662 @default.
- W3176255692 cites W1885185971 @default.
- W3176255692 cites W2102166818 @default.
- W3176255692 cites W2122086266 @default.
- W3176255692 cites W2124187578 @default.
- W3176255692 cites W2210480155 @default.
- W3176255692 cites W2557227117 @default.
- W3176255692 cites W2565312867 @default.
- W3176255692 cites W2768814045 @default.
- W3176255692 cites W2798664922 @default.
- W3176255692 cites W2895957955 @default.
- W3176255692 cites W2948654165 @default.
- W3176255692 cites W2962785568 @default.
- W3176255692 cites W2962927175 @default.
- W3176255692 cites W2963189365 @default.
- W3176255692 cites W2963470893 @default.
- W3176255692 cites W2964035254 @default.
- W3176255692 cites W2964040059 @default.
- W3176255692 cites W2965669158 @default.
- W3176255692 cites W2969260367 @default.
- W3176255692 cites W2973673960 @default.
- W3176255692 cites W2985680812 @default.
- W3176255692 cites W3100087914 @default.
- W3176255692 cites W3102015846 @default.
- W3176255692 cites W3123632567 @default.
- W3176255692 doi "https://doi.org/10.1109/access.2021.3090344" @default.
- W3176255692 hasPublicationYear "2021" @default.
- W3176255692 type Work @default.
- W3176255692 sameAs 3176255692 @default.
- W3176255692 citedByCount "5" @default.
- W3176255692 countsByYear W31762556922021 @default.
- W3176255692 countsByYear W31762556922022 @default.
- W3176255692 countsByYear W31762556922023 @default.
- W3176255692 crossrefType "journal-article" @default.
- W3176255692 hasAuthorship W3176255692A5009469552 @default.
- W3176255692 hasAuthorship W3176255692A5044824896 @default.
- W3176255692 hasAuthorship W3176255692A5045779735 @default.
- W3176255692 hasBestOaLocation W31762556921 @default.
- W3176255692 hasConcept C110384440 @default.
- W3176255692 hasConcept C111919701 @default.
- W3176255692 hasConcept C115961682 @default.
- W3176255692 hasConcept C118505674 @default.
- W3176255692 hasConcept C125411270 @default.
- W3176255692 hasConcept C154945302 @default.
- W3176255692 hasConcept C2987812609 @default.
- W3176255692 hasConcept C34339180 @default.
- W3176255692 hasConcept C41008148 @default.
- W3176255692 hasConcept C57667952 @default.
- W3176255692 hasConcept C78548338 @default.
- W3176255692 hasConcept C79403827 @default.
- W3176255692 hasConceptScore W3176255692C110384440 @default.
- W3176255692 hasConceptScore W3176255692C111919701 @default.
- W3176255692 hasConceptScore W3176255692C115961682 @default.
- W3176255692 hasConceptScore W3176255692C118505674 @default.
- W3176255692 hasConceptScore W3176255692C125411270 @default.
- W3176255692 hasConceptScore W3176255692C154945302 @default.
- W3176255692 hasConceptScore W3176255692C2987812609 @default.
- W3176255692 hasConceptScore W3176255692C34339180 @default.
- W3176255692 hasConceptScore W3176255692C41008148 @default.
- W3176255692 hasConceptScore W3176255692C57667952 @default.
- W3176255692 hasConceptScore W3176255692C78548338 @default.
- W3176255692 hasConceptScore W3176255692C79403827 @default.
- W3176255692 hasLocation W31762556921 @default.
- W3176255692 hasLocation W31762556922 @default.
- W3176255692 hasOpenAccess W3176255692 @default.
- W3176255692 hasPrimaryLocation W31762556921 @default.
- W3176255692 hasRelatedWork W1507609043 @default.
- W3176255692 hasRelatedWork W1516993688 @default.
- W3176255692 hasRelatedWork W1983506731 @default.
- W3176255692 hasRelatedWork W2012995523 @default.
- W3176255692 hasRelatedWork W2058204635 @default.
- W3176255692 hasRelatedWork W2124441525 @default.
- W3176255692 hasRelatedWork W2165538927 @default.
- W3176255692 hasRelatedWork W2965372254 @default.
- W3176255692 hasRelatedWork W4224310085 @default.
- W3176255692 hasRelatedWork W4317600236 @default.
- W3176255692 hasVolume "9" @default.
- W3176255692 isParatext "false" @default.
- W3176255692 isRetracted "false" @default.
- W3176255692 magId "3176255692" @default.
- W3176255692 workType "article" @default.