Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387486933> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4387486933 abstract "The virtual restoration of ancient documents using deep learning is an emergency and an expected work. However, GANs-based image-to-image translation approaches hit the degradation data shortage, a hardness to build one-to-many restoration models, and a limitation for large deformation. In this study, we apply zero-shot restoration based on Diffusion models to ancient degraded documents, specifically, leverage inpainting of Denoing Diffusion Restoration Models (DDRM) for missing ancient characters. Furthermore, we introduce a noise masking method, which limits the attention area of predicted noise images in the reverse process. Noise masking forces DDRM to generate faithful objects following mask images, so that has high usability without re-training of deep neural networks. The zero-shot restoration and noise masking prompt GUI-connecting restoration of missing characters, leading to realizing a cooperative application with humans for ancient document restoration." @default.
- W4387486933 created "2023-10-11" @default.
- W4387486933 creator A5050351696 @default.
- W4387486933 creator A5053005436 @default.
- W4387486933 creator A5076579498 @default.
- W4387486933 creator A5090735898 @default.
- W4387486933 date "2023-09-04" @default.
- W4387486933 modified "2023-10-16" @default.
- W4387486933 title "An Attempt at Zero-shot Ancient Documents Restoration Based on Diffusion Models" @default.
- W4387486933 cites W2010731658 @default.
- W4387486933 cites W2056887119 @default.
- W4387486933 cites W2067142709 @default.
- W4387486933 cites W2114770744 @default.
- W4387486933 cites W2133665775 @default.
- W4387486933 cites W2564188453 @default.
- W4387486933 cites W2962785568 @default.
- W4387486933 cites W2970424822 @default.
- W4387486933 cites W3004377989 @default.
- W4387486933 cites W3045913844 @default.
- W4387486933 cites W3132571997 @default.
- W4387486933 cites W3196915311 @default.
- W4387486933 cites W4220763858 @default.
- W4387486933 cites W4287831878 @default.
- W4387486933 cites W4306948601 @default.
- W4387486933 cites W4309219073 @default.
- W4387486933 cites W4312497550 @default.
- W4387486933 cites W4312533028 @default.
- W4387486933 cites W4313289347 @default.
- W4387486933 cites W4360884927 @default.
- W4387486933 cites W4365509308 @default.
- W4387486933 cites W4379660123 @default.
- W4387486933 cites W4381986098 @default.
- W4387486933 doi "https://doi.org/10.1109/icamechs59878.2023.10272811" @default.
- W4387486933 hasPublicationYear "2023" @default.
- W4387486933 type Work @default.
- W4387486933 citedByCount "0" @default.
- W4387486933 crossrefType "proceedings-article" @default.
- W4387486933 hasAuthorship W4387486933A5050351696 @default.
- W4387486933 hasAuthorship W4387486933A5053005436 @default.
- W4387486933 hasAuthorship W4387486933A5076579498 @default.
- W4387486933 hasAuthorship W4387486933A5090735898 @default.
- W4387486933 hasConcept C106430172 @default.
- W4387486933 hasConcept C107457646 @default.
- W4387486933 hasConcept C115961682 @default.
- W4387486933 hasConcept C11727466 @default.
- W4387486933 hasConcept C142362112 @default.
- W4387486933 hasConcept C153083717 @default.
- W4387486933 hasConcept C153349607 @default.
- W4387486933 hasConcept C154945302 @default.
- W4387486933 hasConcept C170130773 @default.
- W4387486933 hasConcept C200873422 @default.
- W4387486933 hasConcept C2777402240 @default.
- W4387486933 hasConcept C31972630 @default.
- W4387486933 hasConcept C41008148 @default.
- W4387486933 hasConcept C9417928 @default.
- W4387486933 hasConcept C99498987 @default.
- W4387486933 hasConceptScore W4387486933C106430172 @default.
- W4387486933 hasConceptScore W4387486933C107457646 @default.
- W4387486933 hasConceptScore W4387486933C115961682 @default.
- W4387486933 hasConceptScore W4387486933C11727466 @default.
- W4387486933 hasConceptScore W4387486933C142362112 @default.
- W4387486933 hasConceptScore W4387486933C153083717 @default.
- W4387486933 hasConceptScore W4387486933C153349607 @default.
- W4387486933 hasConceptScore W4387486933C154945302 @default.
- W4387486933 hasConceptScore W4387486933C170130773 @default.
- W4387486933 hasConceptScore W4387486933C200873422 @default.
- W4387486933 hasConceptScore W4387486933C2777402240 @default.
- W4387486933 hasConceptScore W4387486933C31972630 @default.
- W4387486933 hasConceptScore W4387486933C41008148 @default.
- W4387486933 hasConceptScore W4387486933C9417928 @default.
- W4387486933 hasConceptScore W4387486933C99498987 @default.
- W4387486933 hasLocation W43874869331 @default.
- W4387486933 hasOpenAccess W4387486933 @default.
- W4387486933 hasPrimaryLocation W43874869331 @default.
- W4387486933 hasRelatedWork W1523707610 @default.
- W4387486933 hasRelatedWork W2012197282 @default.
- W4387486933 hasRelatedWork W2095195575 @default.
- W4387486933 hasRelatedWork W2166862237 @default.
- W4387486933 hasRelatedWork W2350879130 @default.
- W4387486933 hasRelatedWork W2731478784 @default.
- W4387486933 hasRelatedWork W2897194722 @default.
- W4387486933 hasRelatedWork W4221141925 @default.
- W4387486933 hasRelatedWork W4285483878 @default.
- W4387486933 hasRelatedWork W4293869205 @default.
- W4387486933 isParatext "false" @default.
- W4387486933 isRetracted "false" @default.
- W4387486933 workType "article" @default.