Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034239311> ?p ?o ?g. }
- W3034239311 abstract "Lacking rich and realistic data, learned single image denoising algorithms generalize poorly in real raw images that not resemble the data used for training. Although the problem can be alleviated by the heteroscedastic Gaussian noise model, the noise sources caused by digital camera electronics are still largely overlooked, despite their significant effect on raw measurement, especially under extremely low-light condition. To address this issue, we present a highly accurate noise formation model based on the characteristics of CMOS photosensors, thereby enabling us to synthesize realistic samples that better match the physics of image formation process. Given the proposed noise model, we additionally propose a method to calibrate the noise parameters for available modern digital cameras, which is simple and reproducible for any new device. We systematically study the generalizability of a neural network trained with existing schemes, by introducing a new low-light denoising dataset that covers many modern digital cameras from diverse brands. Extensive empirical results collectively show that by utilizing our proposed noise formation model, a network can reach the capability as if it had been trained with rich real data, which demonstrates the effectiveness of our noise formation model." @default.
- W3034239311 created "2020-06-19" @default.
- W3034239311 creator A5022334521 @default.
- W3034239311 creator A5067800206 @default.
- W3034239311 creator A5076804411 @default.
- W3034239311 creator A5083586618 @default.
- W3034239311 date "2020-06-01" @default.
- W3034239311 modified "2023-10-16" @default.
- W3034239311 title "A Physics-Based Noise Formation Model for Extreme Low-Light Raw Denoising" @default.
- W3034239311 cites W1915360731 @default.
- W3034239311 cites W1971935137 @default.
- W3034239311 cites W1993648443 @default.
- W3034239311 cites W2011181254 @default.
- W3034239311 cites W2018612061 @default.
- W3034239311 cites W2038102640 @default.
- W3034239311 cites W2043981759 @default.
- W3034239311 cites W2045079989 @default.
- W3034239311 cites W2048265032 @default.
- W3034239311 cites W2048695508 @default.
- W3034239311 cites W2054274917 @default.
- W3034239311 cites W2056370875 @default.
- W3034239311 cites W2060015546 @default.
- W3034239311 cites W2070094114 @default.
- W3034239311 cites W2071005004 @default.
- W3034239311 cites W2074145713 @default.
- W3034239311 cites W2097073572 @default.
- W3034239311 cites W2103559027 @default.
- W3034239311 cites W2108238208 @default.
- W3034239311 cites W2113316891 @default.
- W3034239311 cites W2114122776 @default.
- W3034239311 cites W2117894815 @default.
- W3034239311 cites W2119449517 @default.
- W3034239311 cites W2130975789 @default.
- W3034239311 cites W2136035751 @default.
- W3034239311 cites W2141759354 @default.
- W3034239311 cites W2153663612 @default.
- W3034239311 cites W2163446914 @default.
- W3034239311 cites W2219841864 @default.
- W3034239311 cites W2508457857 @default.
- W3034239311 cites W2552290192 @default.
- W3034239311 cites W2556872594 @default.
- W3034239311 cites W2566193750 @default.
- W3034239311 cites W2744769585 @default.
- W3034239311 cites W2799192307 @default.
- W3034239311 cites W2799265886 @default.
- W3034239311 cites W2902857081 @default.
- W3034239311 cites W2952323569 @default.
- W3034239311 cites W2962767526 @default.
- W3034239311 cites W2963200935 @default.
- W3034239311 cites W2963725279 @default.
- W3034239311 cites W2964125708 @default.
- W3034239311 cites W2986422266 @default.
- W3034239311 cites W2988641380 @default.
- W3034239311 cites W2989193306 @default.
- W3034239311 cites W2989268192 @default.
- W3034239311 cites W2998334235 @default.
- W3034239311 cites W3123908264 @default.
- W3034239311 cites W4248173958 @default.
- W3034239311 doi "https://doi.org/10.1109/cvpr42600.2020.00283" @default.
- W3034239311 hasPublicationYear "2020" @default.
- W3034239311 type Work @default.
- W3034239311 sameAs 3034239311 @default.
- W3034239311 citedByCount "98" @default.
- W3034239311 countsByYear W30342393112020 @default.
- W3034239311 countsByYear W30342393112021 @default.
- W3034239311 countsByYear W30342393112022 @default.
- W3034239311 countsByYear W30342393112023 @default.
- W3034239311 crossrefType "proceedings-article" @default.
- W3034239311 hasAuthorship W3034239311A5022334521 @default.
- W3034239311 hasAuthorship W3034239311A5067800206 @default.
- W3034239311 hasAuthorship W3034239311A5076804411 @default.
- W3034239311 hasAuthorship W3034239311A5083586618 @default.
- W3034239311 hasBestOaLocation W30342393112 @default.
- W3034239311 hasConcept C111919701 @default.
- W3034239311 hasConcept C115961682 @default.
- W3034239311 hasConcept C154945302 @default.
- W3034239311 hasConcept C163294075 @default.
- W3034239311 hasConcept C29265498 @default.
- W3034239311 hasConcept C31972630 @default.
- W3034239311 hasConcept C41008148 @default.
- W3034239311 hasConcept C4199805 @default.
- W3034239311 hasConcept C98045186 @default.
- W3034239311 hasConcept C99498987 @default.
- W3034239311 hasConceptScore W3034239311C111919701 @default.
- W3034239311 hasConceptScore W3034239311C115961682 @default.
- W3034239311 hasConceptScore W3034239311C154945302 @default.
- W3034239311 hasConceptScore W3034239311C163294075 @default.
- W3034239311 hasConceptScore W3034239311C29265498 @default.
- W3034239311 hasConceptScore W3034239311C31972630 @default.
- W3034239311 hasConceptScore W3034239311C41008148 @default.
- W3034239311 hasConceptScore W3034239311C4199805 @default.
- W3034239311 hasConceptScore W3034239311C98045186 @default.
- W3034239311 hasConceptScore W3034239311C99498987 @default.
- W3034239311 hasLocation W30342393111 @default.
- W3034239311 hasLocation W30342393112 @default.
- W3034239311 hasOpenAccess W3034239311 @default.
- W3034239311 hasPrimaryLocation W30342393111 @default.
- W3034239311 hasRelatedWork W1986743941 @default.
- W3034239311 hasRelatedWork W2023005931 @default.
- W3034239311 hasRelatedWork W2483420468 @default.