Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213088081> ?p ?o ?g. }
- W3213088081 endingPage "9385" @default.
- W3213088081 startingPage "9372" @default.
- W3213088081 abstract "Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional enhancement techniques almost impossible to apply. Recently, learning-based approaches have shown very promising results for this task since they have substantially more expressive capabilities to allow for improved quality. Motivated by these studies, in this paper, we aim to leverage burst photography to boost the performance and obtain much sharper and more accurate RGB images from extremely dark raw images. The backbone of our proposed framework is a novel coarse-to-fine network architecture that generates high-quality outputs progressively. The coarse network predicts a low-resolution, denoised raw image, which is then fed to the fine network to recover fine-scale details and realistic textures. To further reduce the noise level and improve the color accuracy, we extend this network to a permutation invariant structure so that it takes a burst of low-light images as input and merges information from multiple images at the feature-level. Our experiments demonstrate that our approach leads to perceptually more pleasing results than the state-of-the-art methods by producing more detailed and considerably higher quality images." @default.
- W3213088081 created "2021-11-22" @default.
- W3213088081 creator A5000080119 @default.
- W3213088081 creator A5054198229 @default.
- W3213088081 creator A5074809120 @default.
- W3213088081 date "2021-01-01" @default.
- W3213088081 modified "2023-09-27" @default.
- W3213088081 title "Burst Photography for Learning to Enhance Extremely Dark Images" @default.
- W3213088081 cites W1573077480 @default.
- W3213088081 cites W1964394948 @default.
- W3213088081 cites W1997147589 @default.
- W3213088081 cites W1998393535 @default.
- W3213088081 cites W2001412060 @default.
- W3213088081 cites W2011592399 @default.
- W3213088081 cites W2013628794 @default.
- W3213088081 cites W2056370875 @default.
- W3213088081 cites W2076205488 @default.
- W3213088081 cites W2097073572 @default.
- W3213088081 cites W2103559027 @default.
- W3213088081 cites W2107858703 @default.
- W3213088081 cites W2119449517 @default.
- W3213088081 cites W2125527601 @default.
- W3213088081 cites W2136961432 @default.
- W3213088081 cites W2141704978 @default.
- W3213088081 cites W2150461190 @default.
- W3213088081 cites W2150721269 @default.
- W3213088081 cites W2153663612 @default.
- W3213088081 cites W2160451035 @default.
- W3213088081 cites W2254039850 @default.
- W3213088081 cites W2331128040 @default.
- W3213088081 cites W2468596194 @default.
- W3213088081 cites W2552290192 @default.
- W3213088081 cites W2560533888 @default.
- W3213088081 cites W2566376500 @default.
- W3213088081 cites W2752782242 @default.
- W3213088081 cites W2791071401 @default.
- W3213088081 cites W2798581339 @default.
- W3213088081 cites W2799265886 @default.
- W3213088081 cites W2886787375 @default.
- W3213088081 cites W2895477542 @default.
- W3213088081 cites W2948354154 @default.
- W3213088081 cites W2951979964 @default.
- W3213088081 cites W2952323569 @default.
- W3213088081 cites W2962785568 @default.
- W3213088081 cites W2963200935 @default.
- W3213088081 cites W2963661589 @default.
- W3213088081 cites W2963725279 @default.
- W3213088081 cites W2963800363 @default.
- W3213088081 cites W2963914989 @default.
- W3213088081 cites W2964309429 @default.
- W3213088081 cites W2966431607 @default.
- W3213088081 cites W2980876396 @default.
- W3213088081 cites W2986422266 @default.
- W3213088081 cites W2998334235 @default.
- W3213088081 cites W3011565218 @default.
- W3213088081 cites W3035731588 @default.
- W3213088081 cites W3048373607 @default.
- W3213088081 cites W3104725225 @default.
- W3213088081 cites W3109908659 @default.
- W3213088081 cites W3123908264 @default.
- W3213088081 cites W4237777900 @default.
- W3213088081 cites W4242059867 @default.
- W3213088081 doi "https://doi.org/10.1109/tip.2021.3125394" @default.
- W3213088081 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34788215" @default.
- W3213088081 hasPublicationYear "2021" @default.
- W3213088081 type Work @default.
- W3213088081 sameAs 3213088081 @default.
- W3213088081 citedByCount "5" @default.
- W3213088081 countsByYear W32130880812022 @default.
- W3213088081 countsByYear W32130880812023 @default.
- W3213088081 crossrefType "journal-article" @default.
- W3213088081 hasAuthorship W3213088081A5000080119 @default.
- W3213088081 hasAuthorship W3213088081A5054198229 @default.
- W3213088081 hasAuthorship W3213088081A5074809120 @default.
- W3213088081 hasBestOaLocation W32130880812 @default.
- W3213088081 hasConcept C104317684 @default.
- W3213088081 hasConcept C153083717 @default.
- W3213088081 hasConcept C153180895 @default.
- W3213088081 hasConcept C154945302 @default.
- W3213088081 hasConcept C185592680 @default.
- W3213088081 hasConcept C199360897 @default.
- W3213088081 hasConcept C31972630 @default.
- W3213088081 hasConcept C41008148 @default.
- W3213088081 hasConcept C43521106 @default.
- W3213088081 hasConcept C55493867 @default.
- W3213088081 hasConcept C63479239 @default.
- W3213088081 hasConcept C82990744 @default.
- W3213088081 hasConceptScore W3213088081C104317684 @default.
- W3213088081 hasConceptScore W3213088081C153083717 @default.
- W3213088081 hasConceptScore W3213088081C153180895 @default.
- W3213088081 hasConceptScore W3213088081C154945302 @default.
- W3213088081 hasConceptScore W3213088081C185592680 @default.
- W3213088081 hasConceptScore W3213088081C199360897 @default.
- W3213088081 hasConceptScore W3213088081C31972630 @default.
- W3213088081 hasConceptScore W3213088081C41008148 @default.
- W3213088081 hasConceptScore W3213088081C43521106 @default.
- W3213088081 hasConceptScore W3213088081C55493867 @default.
- W3213088081 hasConceptScore W3213088081C63479239 @default.