Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293094724> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4293094724 endingPage "1" @default.
- W4293094724 startingPage "1" @default.
- W4293094724 abstract "Digital images in real world applications typically undergo a wide variety of quality degradations before compression or re-compression. Existing learning based codecs are typically data-driven, relying on the predefined compression pipeline with pristine or high quality images as the input. However, the images in the wild may exhibit the substantially different characteristics compared to the high quality images, casting major challenges to the learning based image coding. In this paper, we propose a robust noisy image compression framework with the blind assumption on the specific noise type and level. The specifically designed encoder decomposes the representation of visual content into two types of features, including the Features that represent the Intrinsic Content (FIC) and the Features that account for Additive Degradation (FAD). As such, beyond the philosophy of faithfully reconstructing the given image with high fidelity, only FIC needs to be compactly represented and conveyed. The principled disentanglement strategy facilitates the removal of the redundancy from multiple perspectives (e.g., spatial, channel and content), ensuring the handling of a wide variety of noisy images in the wild. Extensive experimental results show that our model can achieve superior performance in terms of the ultimate quality and exhibit the strong generalizability across images degraded by a variety of means. The proposed scheme also points out a new research avenue on learning based compression for images in the wild, which is technically challenging but desirable in practice." @default.
- W4293094724 created "2022-08-26" @default.
- W4293094724 creator A5001770837 @default.
- W4293094724 creator A5008386708 @default.
- W4293094724 creator A5042401810 @default.
- W4293094724 creator A5059659400 @default.
- W4293094724 creator A5063776325 @default.
- W4293094724 creator A5084083030 @default.
- W4293094724 creator A5085560196 @default.
- W4293094724 date "2022-01-01" @default.
- W4293094724 modified "2023-10-18" @default.
- W4293094724 title "Learning-based Compression for Noisy Images in the Wild" @default.
- W4293094724 doi "https://doi.org/10.1109/tcsvt.2022.3200763" @default.
- W4293094724 hasPublicationYear "2022" @default.
- W4293094724 type Work @default.
- W4293094724 citedByCount "3" @default.
- W4293094724 countsByYear W42930947242023 @default.
- W4293094724 crossrefType "journal-article" @default.
- W4293094724 hasAuthorship W4293094724A5001770837 @default.
- W4293094724 hasAuthorship W4293094724A5008386708 @default.
- W4293094724 hasAuthorship W4293094724A5042401810 @default.
- W4293094724 hasAuthorship W4293094724A5059659400 @default.
- W4293094724 hasAuthorship W4293094724A5063776325 @default.
- W4293094724 hasAuthorship W4293094724A5084083030 @default.
- W4293094724 hasAuthorship W4293094724A5085560196 @default.
- W4293094724 hasConcept C105795698 @default.
- W4293094724 hasConcept C111919701 @default.
- W4293094724 hasConcept C115961682 @default.
- W4293094724 hasConcept C118505674 @default.
- W4293094724 hasConcept C13481523 @default.
- W4293094724 hasConcept C136197465 @default.
- W4293094724 hasConcept C152124472 @default.
- W4293094724 hasConcept C153180895 @default.
- W4293094724 hasConcept C154945302 @default.
- W4293094724 hasConcept C161765866 @default.
- W4293094724 hasConcept C179518139 @default.
- W4293094724 hasConcept C2776459999 @default.
- W4293094724 hasConcept C31972630 @default.
- W4293094724 hasConcept C33923547 @default.
- W4293094724 hasConcept C41008148 @default.
- W4293094724 hasConcept C55020928 @default.
- W4293094724 hasConcept C76155785 @default.
- W4293094724 hasConcept C78548338 @default.
- W4293094724 hasConcept C9390403 @default.
- W4293094724 hasConcept C9417928 @default.
- W4293094724 hasConceptScore W4293094724C105795698 @default.
- W4293094724 hasConceptScore W4293094724C111919701 @default.
- W4293094724 hasConceptScore W4293094724C115961682 @default.
- W4293094724 hasConceptScore W4293094724C118505674 @default.
- W4293094724 hasConceptScore W4293094724C13481523 @default.
- W4293094724 hasConceptScore W4293094724C136197465 @default.
- W4293094724 hasConceptScore W4293094724C152124472 @default.
- W4293094724 hasConceptScore W4293094724C153180895 @default.
- W4293094724 hasConceptScore W4293094724C154945302 @default.
- W4293094724 hasConceptScore W4293094724C161765866 @default.
- W4293094724 hasConceptScore W4293094724C179518139 @default.
- W4293094724 hasConceptScore W4293094724C2776459999 @default.
- W4293094724 hasConceptScore W4293094724C31972630 @default.
- W4293094724 hasConceptScore W4293094724C33923547 @default.
- W4293094724 hasConceptScore W4293094724C41008148 @default.
- W4293094724 hasConceptScore W4293094724C55020928 @default.
- W4293094724 hasConceptScore W4293094724C76155785 @default.
- W4293094724 hasConceptScore W4293094724C78548338 @default.
- W4293094724 hasConceptScore W4293094724C9390403 @default.
- W4293094724 hasConceptScore W4293094724C9417928 @default.
- W4293094724 hasLocation W42930947241 @default.
- W4293094724 hasOpenAccess W4293094724 @default.
- W4293094724 hasPrimaryLocation W42930947241 @default.
- W4293094724 hasRelatedWork W1982504210 @default.
- W4293094724 hasRelatedWork W2167373580 @default.
- W4293094724 hasRelatedWork W2264127496 @default.
- W4293094724 hasRelatedWork W2275988210 @default.
- W4293094724 hasRelatedWork W2353272253 @default.
- W4293094724 hasRelatedWork W2368287095 @default.
- W4293094724 hasRelatedWork W3192084598 @default.
- W4293094724 hasRelatedWork W4283699800 @default.
- W4293094724 hasRelatedWork W4283817257 @default.
- W4293094724 hasRelatedWork W4298129431 @default.
- W4293094724 isParatext "false" @default.
- W4293094724 isRetracted "false" @default.
- W4293094724 workType "article" @default.