Matches in SemOpenAlex for { <https://semopenalex.org/work/W3141862816> ?p ?o ?g. }
- W3141862816 abstract "Heterogeneity exists in most camera images. This heterogeneity manifests itself across the image space as varied Moire ringing, motion-blur, color-bleaching or lens based projection distortions. Moreover, combinations of these image artifacts can be present in small or large pixel neighborhoods, within an acquired image. Current camera image processing pipelines, including deep trained versions, tend to rectify the issue applying a single filter that is homogeneously applied to the entire image. This is also particularly true when an encoder-decoder type deep architecture is trained for the task. In this paper, we present a structured deep learning model that solves the heterogeneous image artifact filtering problem. We call our deep trained model the Patch Subspace Variational Autoencoder (PS-VAE) for Camera ISP. PS-VAE does not necessarily assume uniform image distortion levels nor similar artifact types within the image. Rather, our model attempts to learn to cluster different patches extracted from images into artifact type and distortion levels, within multiple latent subspaces (e.g. Moire ringing artifacts are often a higher dimensional latent distortion than a Gaussian motion blur artifact). Each image's patches are encoded into soft-clusters in their appropriate latent sub-space, using a prior mixture model. The decoders of the PS-VAE are also trained in an unsupervised manner for each of the image patches in each soft-cluster. Our experimental results demonstrates the flexibility and performance that one can achieve through improved heterogeneous filtering. We compare our results to a conventional one-encoder-one-decoder architecture." @default.
- W3141862816 created "2021-04-13" @default.
- W3141862816 creator A5006394426 @default.
- W3141862816 creator A5022908200 @default.
- W3141862816 creator A5028878390 @default.
- W3141862816 creator A5071606862 @default.
- W3141862816 date "2021-04-01" @default.
- W3141862816 modified "2023-10-05" @default.
- W3141862816 title "Learning Deep Latent Subspaces for Image Denoising." @default.
- W3141862816 cites W1834627138 @default.
- W3141862816 cites W1901129140 @default.
- W3141862816 cites W1959608418 @default.
- W3141862816 cites W1966855663 @default.
- W3141862816 cites W1982978748 @default.
- W3141862816 cites W2035192779 @default.
- W3141862816 cites W2056370875 @default.
- W3141862816 cites W2069051299 @default.
- W3141862816 cites W2097073572 @default.
- W3141862816 cites W2103559027 @default.
- W3141862816 cites W2133665775 @default.
- W3141862816 cites W2139118119 @default.
- W3141862816 cites W2149925139 @default.
- W3141862816 cites W2159269332 @default.
- W3141862816 cites W2160547390 @default.
- W3141862816 cites W2242218935 @default.
- W3141862816 cites W2508457857 @default.
- W3141862816 cites W2533545350 @default.
- W3141862816 cites W2556467266 @default.
- W3141862816 cites W2556872594 @default.
- W3141862816 cites W2572006047 @default.
- W3141862816 cites W2604977777 @default.
- W3141862816 cites W2607202125 @default.
- W3141862816 cites W2796704765 @default.
- W3141862816 cites W2799192307 @default.
- W3141862816 cites W2892210823 @default.
- W3141862816 cites W2902857081 @default.
- W3141862816 cites W2938390807 @default.
- W3141862816 cites W2949064199 @default.
- W3141862816 cites W2952046917 @default.
- W3141862816 cites W2962687329 @default.
- W3141862816 cites W2962767526 @default.
- W3141862816 cites W2962818303 @default.
- W3141862816 cites W2962974533 @default.
- W3141862816 cites W2963073614 @default.
- W3141862816 cites W2963470893 @default.
- W3141862816 cites W2963725279 @default.
- W3141862816 cites W2963762505 @default.
- W3141862816 cites W2964121744 @default.
- W3141862816 cites W2983356984 @default.
- W3141862816 cites W2997247224 @default.
- W3141862816 cites W3002691622 @default.
- W3141862816 cites W3034504121 @default.
- W3141862816 cites W3034695079 @default.
- W3141862816 cites W3034789174 @default.
- W3141862816 cites W3034794187 @default.
- W3141862816 cites W3034902810 @default.
- W3141862816 cites W3035381835 @default.
- W3141862816 cites W3047011367 @default.
- W3141862816 cites W3048092834 @default.
- W3141862816 cites W3098337560 @default.
- W3141862816 cites W3100866725 @default.
- W3141862816 cites W3210232381 @default.
- W3141862816 hasPublicationYear "2021" @default.
- W3141862816 type Work @default.
- W3141862816 sameAs 3141862816 @default.
- W3141862816 citedByCount "2" @default.
- W3141862816 countsByYear W31418628162021 @default.
- W3141862816 crossrefType "posted-content" @default.
- W3141862816 hasAuthorship W3141862816A5006394426 @default.
- W3141862816 hasAuthorship W3141862816A5022908200 @default.
- W3141862816 hasAuthorship W3141862816A5028878390 @default.
- W3141862816 hasAuthorship W3141862816A5071606862 @default.
- W3141862816 hasConcept C115961682 @default.
- W3141862816 hasConcept C126780896 @default.
- W3141862816 hasConcept C153180895 @default.
- W3141862816 hasConcept C154945302 @default.
- W3141862816 hasConcept C17828673 @default.
- W3141862816 hasConcept C194257627 @default.
- W3141862816 hasConcept C2776257435 @default.
- W3141862816 hasConcept C31258907 @default.
- W3141862816 hasConcept C31972630 @default.
- W3141862816 hasConcept C41008148 @default.
- W3141862816 hasConceptScore W3141862816C115961682 @default.
- W3141862816 hasConceptScore W3141862816C126780896 @default.
- W3141862816 hasConceptScore W3141862816C153180895 @default.
- W3141862816 hasConceptScore W3141862816C154945302 @default.
- W3141862816 hasConceptScore W3141862816C17828673 @default.
- W3141862816 hasConceptScore W3141862816C194257627 @default.
- W3141862816 hasConceptScore W3141862816C2776257435 @default.
- W3141862816 hasConceptScore W3141862816C31258907 @default.
- W3141862816 hasConceptScore W3141862816C31972630 @default.
- W3141862816 hasConceptScore W3141862816C41008148 @default.
- W3141862816 hasLocation W31418628161 @default.
- W3141862816 hasOpenAccess W3141862816 @default.
- W3141862816 hasPrimaryLocation W31418628161 @default.
- W3141862816 hasRelatedWork W2007590272 @default.
- W3141862816 hasRelatedWork W2061398022 @default.
- W3141862816 hasRelatedWork W2071057855 @default.
- W3141862816 hasRelatedWork W2080794127 @default.
- W3141862816 hasRelatedWork W2092144522 @default.