Matches in SemOpenAlex for { <https://semopenalex.org/work/W3115247977> ?p ?o ?g. }
- W3115247977 abstract "We seek to reconstruct sharp and noise-free high-dynamic range (HDR) video from a dual-exposure sensor that records different low-dynamic range (LDR) information in different pixel columns: Odd columns provide low-exposure, sharp, but noisy information; even columns complement this with less noisy, high-exposure, but motion-blurred data. Previous LDR work learns to deblur and denoise (DISTORTED->CLEAN) supervised by pairs of CLEAN and DISTORTED images. Regrettably, capturing DISTORTED sensor readings is time-consuming; as well, there is a lack of CLEAN HDR videos. We suggest a method to overcome those two limitations. First, we learn a different function instead: CLEAN->DISTORTED, which generates samples containing correlated pixel noise, and row and column noise, as well as motion blur from a low number of CLEAN sensor readings. Second, as there is not enough CLEAN HDR video available, we devise a method to learn from LDR video in-stead. Our approach compares favorably to several strong baselines, and can boost existing methods when they are re-trained on our data. Combined with spatial and temporal super-resolution, it enables applications such as re-lighting with low noise or blur." @default.
- W3115247977 created "2021-01-05" @default.
- W3115247977 creator A5005460704 @default.
- W3115247977 creator A5014909371 @default.
- W3115247977 creator A5058028526 @default.
- W3115247977 creator A5076048449 @default.
- W3115247977 creator A5084442493 @default.
- W3115247977 date "2020-12-22" @default.
- W3115247977 modified "2023-09-27" @default.
- W3115247977 title "HDR Denoising and Deblurring by Learning Spatio-temporal Distortion Models" @default.
- W3115247977 cites W1505723240 @default.
- W3115247977 cites W1598281290 @default.
- W3115247977 cites W1901129140 @default.
- W3115247977 cites W1916935112 @default.
- W3115247977 cites W1917431891 @default.
- W3115247977 cites W1973567017 @default.
- W3115247977 cites W1980076050 @default.
- W3115247977 cites W1991970753 @default.
- W3115247977 cites W2020799651 @default.
- W3115247977 cites W2021347102 @default.
- W3115247977 cites W2033686334 @default.
- W3115247977 cites W2037391681 @default.
- W3115247977 cites W2037642501 @default.
- W3115247977 cites W2042851294 @default.
- W3115247977 cites W2043529138 @default.
- W3115247977 cites W204742108 @default.
- W3115247977 cites W2048695508 @default.
- W3115247977 cites W2056370875 @default.
- W3115247977 cites W2069281566 @default.
- W3115247977 cites W2080701608 @default.
- W3115247977 cites W2092245620 @default.
- W3115247977 cites W2097073572 @default.
- W3115247977 cites W2098535678 @default.
- W3115247977 cites W2098691629 @default.
- W3115247977 cites W2099628070 @default.
- W3115247977 cites W2099770336 @default.
- W3115247977 cites W2101305476 @default.
- W3115247977 cites W2103802376 @default.
- W3115247977 cites W2119449517 @default.
- W3115247977 cites W2123104601 @default.
- W3115247977 cites W2124964692 @default.
- W3115247977 cites W2130700878 @default.
- W3115247977 cites W2133665775 @default.
- W3115247977 cites W2138204001 @default.
- W3115247977 cites W2152398183 @default.
- W3115247977 cites W2157439470 @default.
- W3115247977 cites W2158201077 @default.
- W3115247977 cites W2159736423 @default.
- W3115247977 cites W2163446914 @default.
- W3115247977 cites W2172275395 @default.
- W3115247977 cites W2194775991 @default.
- W3115247977 cites W2240434622 @default.
- W3115247977 cites W2293879958 @default.
- W3115247977 cites W2300657047 @default.
- W3115247977 cites W2304846792 @default.
- W3115247977 cites W233979554 @default.
- W3115247977 cites W2476548250 @default.
- W3115247977 cites W2508457857 @default.
- W3115247977 cites W2523714292 @default.
- W3115247977 cites W2552290192 @default.
- W3115247977 cites W2560533888 @default.
- W3115247977 cites W2562637781 @default.
- W3115247977 cites W2564023417 @default.
- W3115247977 cites W2609107023 @default.
- W3115247977 cites W2736611505 @default.
- W3115247977 cites W2738579427 @default.
- W3115247977 cites W2738652023 @default.
- W3115247977 cites W2769930525 @default.
- W3115247977 cites W2774659647 @default.
- W3115247977 cites W277686387 @default.
- W3115247977 cites W2786718214 @default.
- W3115247977 cites W2798278116 @default.
- W3115247977 cites W2799265886 @default.
- W3115247977 cites W2883566908 @default.
- W3115247977 cites W2895477542 @default.
- W3115247977 cites W2900524642 @default.
- W3115247977 cites W2902857081 @default.
- W3115247977 cites W2914204228 @default.
- W3115247977 cites W2950116990 @default.
- W3115247977 cites W2953823547 @default.
- W3115247977 cites W2962767526 @default.
- W3115247977 cites W2962793481 @default.
- W3115247977 cites W2963050774 @default.
- W3115247977 cites W2963136136 @default.
- W3115247977 cites W2963200935 @default.
- W3115247977 cites W2963312584 @default.
- W3115247977 cites W2963530785 @default.
- W3115247977 cites W2963686971 @default.
- W3115247977 cites W2963725279 @default.
- W3115247977 cites W2964013315 @default.
- W3115247977 cites W2964030969 @default.
- W3115247977 cites W2964046669 @default.
- W3115247977 cites W2964076515 @default.
- W3115247977 cites W2964204553 @default.
- W3115247977 cites W2964317599 @default.
- W3115247977 cites W2967205412 @default.
- W3115247977 cites W2969598820 @default.
- W3115247977 cites W2971082124 @default.
- W3115247977 cites W2972708139 @default.
- W3115247977 cites W2982795046 @default.