Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313306230> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4313306230 endingPage "13" @default.
- W4313306230 startingPage "1" @default.
- W4313306230 abstract "Recently, supervised deep-learning methods have shown their effectiveness on raw video denoising in low-light. However, existing training datasets have specific drawbacks, <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>e.g.</i> , inaccurate noise modeling in synthetic datasets, simple motion created by hand or fixed motion, and limited-quality ground truth caused by the beam splitter in real captured datasets. These defects significantly decline the performance of network when tackling real low-light video sequences, where noise distribution and motion patterns are extremely complex. In this paper, we collect a raw video denoising dataset in low-light with complex motion and high-quality ground truth, overcoming the drawbacks of previous datasets. Specifically, we capture 210 paired videos, each containing short/long exposure pairs of real video frames with dynamic objects and diverse scenes displayed on a high-end monitor. Besides, since spatial self-similarity has been extensively utilized in image tasks, harnessing this property for network design is more crucial for video denoising as temporal redundancy. To effectively exploit the intrinsic temporal-spatial self-similarity of complex motion in real videos, we propose a new Transformer-based network, which can effectively combine the locality of convolution with the long-range modeling ability of 3D temporal-spatial self-attention. Extensive experiments verify the value of our dataset and the effectiveness of our method on various metrics." @default.
- W4313306230 created "2023-01-06" @default.
- W4313306230 creator A5007653701 @default.
- W4313306230 creator A5067800206 @default.
- W4313306230 creator A5071672663 @default.
- W4313306230 creator A5072794263 @default.
- W4313306230 date "2022-01-01" @default.
- W4313306230 modified "2023-10-15" @default.
- W4313306230 title "Low-light Raw Video Denoising with a High-quality Realistic Motion Dataset" @default.
- W4313306230 doi "https://doi.org/10.1109/tmm.2022.3233247" @default.
- W4313306230 hasPublicationYear "2022" @default.
- W4313306230 type Work @default.
- W4313306230 citedByCount "2" @default.
- W4313306230 countsByYear W43133062302023 @default.
- W4313306230 crossrefType "journal-article" @default.
- W4313306230 hasAuthorship W4313306230A5007653701 @default.
- W4313306230 hasAuthorship W4313306230A5067800206 @default.
- W4313306230 hasAuthorship W4313306230A5071672663 @default.
- W4313306230 hasAuthorship W4313306230A5072794263 @default.
- W4313306230 hasConcept C111919701 @default.
- W4313306230 hasConcept C115961682 @default.
- W4313306230 hasConcept C128840427 @default.
- W4313306230 hasConcept C138885662 @default.
- W4313306230 hasConcept C146849305 @default.
- W4313306230 hasConcept C152124472 @default.
- W4313306230 hasConcept C153180895 @default.
- W4313306230 hasConcept C154945302 @default.
- W4313306230 hasConcept C163294075 @default.
- W4313306230 hasConcept C2777708103 @default.
- W4313306230 hasConcept C2779808786 @default.
- W4313306230 hasConcept C31972630 @default.
- W4313306230 hasConcept C41008148 @default.
- W4313306230 hasConcept C41895202 @default.
- W4313306230 hasConcept C99498987 @default.
- W4313306230 hasConceptScore W4313306230C111919701 @default.
- W4313306230 hasConceptScore W4313306230C115961682 @default.
- W4313306230 hasConceptScore W4313306230C128840427 @default.
- W4313306230 hasConceptScore W4313306230C138885662 @default.
- W4313306230 hasConceptScore W4313306230C146849305 @default.
- W4313306230 hasConceptScore W4313306230C152124472 @default.
- W4313306230 hasConceptScore W4313306230C153180895 @default.
- W4313306230 hasConceptScore W4313306230C154945302 @default.
- W4313306230 hasConceptScore W4313306230C163294075 @default.
- W4313306230 hasConceptScore W4313306230C2777708103 @default.
- W4313306230 hasConceptScore W4313306230C2779808786 @default.
- W4313306230 hasConceptScore W4313306230C31972630 @default.
- W4313306230 hasConceptScore W4313306230C41008148 @default.
- W4313306230 hasConceptScore W4313306230C41895202 @default.
- W4313306230 hasConceptScore W4313306230C99498987 @default.
- W4313306230 hasFunder F4320321001 @default.
- W4313306230 hasLocation W43133062301 @default.
- W4313306230 hasOpenAccess W4313306230 @default.
- W4313306230 hasPrimaryLocation W43133062301 @default.
- W4313306230 hasRelatedWork W1529687106 @default.
- W4313306230 hasRelatedWork W2013725854 @default.
- W4313306230 hasRelatedWork W2056979260 @default.
- W4313306230 hasRelatedWork W2081458845 @default.
- W4313306230 hasRelatedWork W3080585449 @default.
- W4313306230 hasRelatedWork W3176165731 @default.
- W4313306230 hasRelatedWork W3195523115 @default.
- W4313306230 hasRelatedWork W3202748844 @default.
- W4313306230 hasRelatedWork W3210545371 @default.
- W4313306230 hasRelatedWork W4206673776 @default.
- W4313306230 isParatext "false" @default.
- W4313306230 isRetracted "false" @default.
- W4313306230 workType "article" @default.