Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224933788> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4224933788 abstract "Hand-held photography in low-light conditions presents a number of challenges to capture high quality images. Capturing using a high ISO results in noisy images, while capturing using longer exposure results in blurry images. This necessitates post-processing techniques to restore the latent image. Most existing methods try to estimate the latent image either by denoising or by deblurring a single image. Both these approaches are ill-posed and often result in unsatisfactory results. A few methods try to alleviate this ill-posedness using a pair of noisy-blurry images as inputs. However, most of the methods using this approach are computationally very expensive. In this paper, we propose a fast method to estimate a latent image given a pair of noisy-blurry images. To accomplish this, we propose a deep-learning based approach that uses scale space representation of the images. To improve computational efficiency, we process higher scale spaces using shallower networks and the lowest scale using a deeper network. Also, unlike existing scale-space methods that use bi-cubic interpolation, we propose a content preserving scale space transformation for decimation and interpolation. The proposed method generates state-of-the-art results at reduced computational complexity compared to state-of-the-art method. Finally, we also show that computational efficiency can be improved by 90% compared to baseline with only a marginal drop in PSNR." @default.
- W4224933788 created "2022-04-28" @default.
- W4224933788 creator A5036945791 @default.
- W4224933788 creator A5038678679 @default.
- W4224933788 creator A5053565922 @default.
- W4224933788 creator A5056104455 @default.
- W4224933788 date "2022-05-23" @default.
- W4224933788 modified "2023-10-16" @default.
- W4224933788 title "Content Preserving Scale Space Network for Fast Image Restoration from Noisy-Blurry Pairs" @default.
- W4224933788 cites W1910136096 @default.
- W4224933788 cites W2056370875 @default.
- W4224933788 cites W2099770336 @default.
- W4224933788 cites W2560533888 @default.
- W4224933788 cites W2883566908 @default.
- W4224933788 cites W2961218591 @default.
- W4224933788 cites W2963725279 @default.
- W4224933788 cites W2983315964 @default.
- W4224933788 cites W3034504121 @default.
- W4224933788 cites W3034789174 @default.
- W4224933788 cites W3104725225 @default.
- W4224933788 cites W3170697543 @default.
- W4224933788 doi "https://doi.org/10.1109/icassp43922.2022.9746495" @default.
- W4224933788 hasPublicationYear "2022" @default.
- W4224933788 type Work @default.
- W4224933788 citedByCount "0" @default.
- W4224933788 crossrefType "proceedings-article" @default.
- W4224933788 hasAuthorship W4224933788A5036945791 @default.
- W4224933788 hasAuthorship W4224933788A5038678679 @default.
- W4224933788 hasAuthorship W4224933788A5053565922 @default.
- W4224933788 hasAuthorship W4224933788A5056104455 @default.
- W4224933788 hasConcept C106430172 @default.
- W4224933788 hasConcept C111919701 @default.
- W4224933788 hasConcept C115961682 @default.
- W4224933788 hasConcept C141379421 @default.
- W4224933788 hasConcept C154945302 @default.
- W4224933788 hasConcept C205649164 @default.
- W4224933788 hasConcept C2778572836 @default.
- W4224933788 hasConcept C2778755073 @default.
- W4224933788 hasConcept C31972630 @default.
- W4224933788 hasConcept C41008148 @default.
- W4224933788 hasConcept C58640448 @default.
- W4224933788 hasConcept C9417928 @default.
- W4224933788 hasConcept C99102927 @default.
- W4224933788 hasConceptScore W4224933788C106430172 @default.
- W4224933788 hasConceptScore W4224933788C111919701 @default.
- W4224933788 hasConceptScore W4224933788C115961682 @default.
- W4224933788 hasConceptScore W4224933788C141379421 @default.
- W4224933788 hasConceptScore W4224933788C154945302 @default.
- W4224933788 hasConceptScore W4224933788C205649164 @default.
- W4224933788 hasConceptScore W4224933788C2778572836 @default.
- W4224933788 hasConceptScore W4224933788C2778755073 @default.
- W4224933788 hasConceptScore W4224933788C31972630 @default.
- W4224933788 hasConceptScore W4224933788C41008148 @default.
- W4224933788 hasConceptScore W4224933788C58640448 @default.
- W4224933788 hasConceptScore W4224933788C9417928 @default.
- W4224933788 hasConceptScore W4224933788C99102927 @default.
- W4224933788 hasLocation W42249337881 @default.
- W4224933788 hasOpenAccess W4224933788 @default.
- W4224933788 hasPrimaryLocation W42249337881 @default.
- W4224933788 hasRelatedWork W1533292911 @default.
- W4224933788 hasRelatedWork W2046133581 @default.
- W4224933788 hasRelatedWork W2076843379 @default.
- W4224933788 hasRelatedWork W2080322084 @default.
- W4224933788 hasRelatedWork W2130228941 @default.
- W4224933788 hasRelatedWork W2132132164 @default.
- W4224933788 hasRelatedWork W3044651058 @default.
- W4224933788 hasRelatedWork W3093404388 @default.
- W4224933788 hasRelatedWork W3123424645 @default.
- W4224933788 hasRelatedWork W3152929143 @default.
- W4224933788 isParatext "false" @default.
- W4224933788 isRetracted "false" @default.
- W4224933788 workType "article" @default.