Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327992893> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4327992893 abstract "With well-selected data, homogeneous diffusion inpainting can reconstruct images from sparse data with high quality. While 4K colour images of size 3840 x 2160 can already be inpainted in real time, optimising the known data for applications like image compression remains challenging: Widely used stochastic strategies can take days for a single 4K image. Recently, a first neural approach for this so-called mask optimisation problem offered high speed and good quality for small images. It trains a mask generation network with the help of a neural inpainting surrogate. However, these mask networks can only output masks for the resolution and mask density they were trained for. We solve these problems and enable mask optimisation for high-resolution images through a neuroexplicit coarse-to-fine strategy. Additionally, we improve the training and interpretability of mask networks by including a numerical inpainting solver directly into the network. This allows to generate masks for 4K images in around 0.6 seconds while exceeding the quality of stochastic methods on practically relevant densities. Compared to popular existing approaches, this is an acceleration of up to four orders of magnitude." @default.
- W4327992893 created "2023-03-21" @default.
- W4327992893 creator A5005009066 @default.
- W4327992893 creator A5007086183 @default.
- W4327992893 creator A5009100118 @default.
- W4327992893 creator A5039895188 @default.
- W4327992893 date "2023-03-17" @default.
- W4327992893 modified "2023-09-26" @default.
- W4327992893 title "Efficient Neural Generation of 4K Masks for Homogeneous Diffusion Inpainting" @default.
- W4327992893 doi "https://doi.org/10.48550/arxiv.2303.10096" @default.
- W4327992893 hasPublicationYear "2023" @default.
- W4327992893 type Work @default.
- W4327992893 citedByCount "0" @default.
- W4327992893 crossrefType "posted-content" @default.
- W4327992893 hasAuthorship W4327992893A5005009066 @default.
- W4327992893 hasAuthorship W4327992893A5007086183 @default.
- W4327992893 hasAuthorship W4327992893A5009100118 @default.
- W4327992893 hasAuthorship W4327992893A5039895188 @default.
- W4327992893 hasConcept C11413529 @default.
- W4327992893 hasConcept C114614502 @default.
- W4327992893 hasConcept C115961682 @default.
- W4327992893 hasConcept C11727466 @default.
- W4327992893 hasConcept C117896860 @default.
- W4327992893 hasConcept C121332964 @default.
- W4327992893 hasConcept C127759330 @default.
- W4327992893 hasConcept C154945302 @default.
- W4327992893 hasConcept C173801870 @default.
- W4327992893 hasConcept C199360897 @default.
- W4327992893 hasConcept C2778770139 @default.
- W4327992893 hasConcept C2781067378 @default.
- W4327992893 hasConcept C31972630 @default.
- W4327992893 hasConcept C33923547 @default.
- W4327992893 hasConcept C41008148 @default.
- W4327992893 hasConcept C50644808 @default.
- W4327992893 hasConcept C55020928 @default.
- W4327992893 hasConcept C66882249 @default.
- W4327992893 hasConcept C69357855 @default.
- W4327992893 hasConcept C74650414 @default.
- W4327992893 hasConcept C97355855 @default.
- W4327992893 hasConceptScore W4327992893C11413529 @default.
- W4327992893 hasConceptScore W4327992893C114614502 @default.
- W4327992893 hasConceptScore W4327992893C115961682 @default.
- W4327992893 hasConceptScore W4327992893C11727466 @default.
- W4327992893 hasConceptScore W4327992893C117896860 @default.
- W4327992893 hasConceptScore W4327992893C121332964 @default.
- W4327992893 hasConceptScore W4327992893C127759330 @default.
- W4327992893 hasConceptScore W4327992893C154945302 @default.
- W4327992893 hasConceptScore W4327992893C173801870 @default.
- W4327992893 hasConceptScore W4327992893C199360897 @default.
- W4327992893 hasConceptScore W4327992893C2778770139 @default.
- W4327992893 hasConceptScore W4327992893C2781067378 @default.
- W4327992893 hasConceptScore W4327992893C31972630 @default.
- W4327992893 hasConceptScore W4327992893C33923547 @default.
- W4327992893 hasConceptScore W4327992893C41008148 @default.
- W4327992893 hasConceptScore W4327992893C50644808 @default.
- W4327992893 hasConceptScore W4327992893C55020928 @default.
- W4327992893 hasConceptScore W4327992893C66882249 @default.
- W4327992893 hasConceptScore W4327992893C69357855 @default.
- W4327992893 hasConceptScore W4327992893C74650414 @default.
- W4327992893 hasConceptScore W4327992893C97355855 @default.
- W4327992893 hasLocation W43279928931 @default.
- W4327992893 hasOpenAccess W4327992893 @default.
- W4327992893 hasPrimaryLocation W43279928931 @default.
- W4327992893 hasRelatedWork W1533292911 @default.
- W4327992893 hasRelatedWork W1574999717 @default.
- W4327992893 hasRelatedWork W2005185696 @default.
- W4327992893 hasRelatedWork W2020564930 @default.
- W4327992893 hasRelatedWork W2059339452 @default.
- W4327992893 hasRelatedWork W2076843379 @default.
- W4327992893 hasRelatedWork W2262668847 @default.
- W4327992893 hasRelatedWork W2574052219 @default.
- W4327992893 hasRelatedWork W2995115364 @default.
- W4327992893 hasRelatedWork W4292794826 @default.
- W4327992893 isParatext "false" @default.
- W4327992893 isRetracted "false" @default.
- W4327992893 workType "article" @default.