Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328124783> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4328124783 endingPage "3972" @default.
- W4328124783 startingPage "3972" @default.
- W4328124783 abstract "As the only underground mural in the collection, the tomb murals are subject to damage due to temperature, humidity, and foundation settlement changes. Traditional mural inpainting takes a long time and requires experts to draw it manually. Therefore, the need for digital inpainting is increasing to save time and costs. Due to the scarcity of samples and the variety of damage, the image features are scattered and partially sparse, and the colors are less vivid than in other images. Traditional deep learning inpainting causes information loss and generates irrational structures. The generative adversarial network is, recently, a more effective method. Therefore, this paper presents an inpainting model based on dual-attention multiscale feature aggregation and an improved generator. Firstly, an improved residual prior and attention mechanism is added to the generator module to preserve the image structure. Secondly, the model combines spatial and channel attention with multiscale feature aggregation to change the mapping network structure and improve the inpainting accuracy. Finally, the segmental loss function and its training method are improved.The experimental results show that the results of using signal-to-noise ratio (PSNR), structural similarity (SSIM), and mean square error (MSE) on epitaxial mask, crack mask, random small mask, and random large mask are better than other methods. It demonstrates the performance of this paper in inpainting different diseases of murals. It can be used as a reference for experts in manual inpainting, saving the cost and time of manual inpainting." @default.
- W4328124783 created "2023-03-22" @default.
- W4328124783 creator A5051893774 @default.
- W4328124783 creator A5054352845 @default.
- W4328124783 creator A5090485617 @default.
- W4328124783 date "2023-03-21" @default.
- W4328124783 modified "2023-09-26" @default.
- W4328124783 title "Fragments Inpainting for Tomb Murals Using a Dual-Attention Mechanism GAN with Improved Generators" @default.
- W4328124783 cites W1986920535 @default.
- W4328124783 cites W1993120651 @default.
- W4328124783 cites W2064309976 @default.
- W4328124783 cites W2105038642 @default.
- W4328124783 cites W2618530766 @default.
- W4328124783 cites W2809598685 @default.
- W4328124783 cites W2884585870 @default.
- W4328124783 cites W2894683476 @default.
- W4328124783 cites W2895822887 @default.
- W4328124783 cites W2951474009 @default.
- W4328124783 cites W2978846005 @default.
- W4328124783 cites W2981682056 @default.
- W4328124783 cites W2989207674 @default.
- W4328124783 cites W3010859369 @default.
- W4328124783 cites W3031651872 @default.
- W4328124783 cites W3035512475 @default.
- W4328124783 cites W3096831136 @default.
- W4328124783 cites W3184736166 @default.
- W4328124783 cites W3199003182 @default.
- W4328124783 cites W3203538104 @default.
- W4328124783 cites W3217062060 @default.
- W4328124783 cites W4293084109 @default.
- W4328124783 cites W4302425267 @default.
- W4328124783 cites W4308502964 @default.
- W4328124783 cites W4313151402 @default.
- W4328124783 doi "https://doi.org/10.3390/app13063972" @default.
- W4328124783 hasPublicationYear "2023" @default.
- W4328124783 type Work @default.
- W4328124783 citedByCount "1" @default.
- W4328124783 countsByYear W43281247832023 @default.
- W4328124783 crossrefType "journal-article" @default.
- W4328124783 hasAuthorship W4328124783A5051893774 @default.
- W4328124783 hasAuthorship W4328124783A5054352845 @default.
- W4328124783 hasAuthorship W4328124783A5090485617 @default.
- W4328124783 hasBestOaLocation W43281247831 @default.
- W4328124783 hasConcept C108583219 @default.
- W4328124783 hasConcept C115961682 @default.
- W4328124783 hasConcept C11727466 @default.
- W4328124783 hasConcept C121332964 @default.
- W4328124783 hasConcept C138885662 @default.
- W4328124783 hasConcept C153180895 @default.
- W4328124783 hasConcept C154945302 @default.
- W4328124783 hasConcept C162307627 @default.
- W4328124783 hasConcept C163258240 @default.
- W4328124783 hasConcept C2776401178 @default.
- W4328124783 hasConcept C2780992000 @default.
- W4328124783 hasConcept C31972630 @default.
- W4328124783 hasConcept C41008148 @default.
- W4328124783 hasConcept C41895202 @default.
- W4328124783 hasConcept C62520636 @default.
- W4328124783 hasConceptScore W4328124783C108583219 @default.
- W4328124783 hasConceptScore W4328124783C115961682 @default.
- W4328124783 hasConceptScore W4328124783C11727466 @default.
- W4328124783 hasConceptScore W4328124783C121332964 @default.
- W4328124783 hasConceptScore W4328124783C138885662 @default.
- W4328124783 hasConceptScore W4328124783C153180895 @default.
- W4328124783 hasConceptScore W4328124783C154945302 @default.
- W4328124783 hasConceptScore W4328124783C162307627 @default.
- W4328124783 hasConceptScore W4328124783C163258240 @default.
- W4328124783 hasConceptScore W4328124783C2776401178 @default.
- W4328124783 hasConceptScore W4328124783C2780992000 @default.
- W4328124783 hasConceptScore W4328124783C31972630 @default.
- W4328124783 hasConceptScore W4328124783C41008148 @default.
- W4328124783 hasConceptScore W4328124783C41895202 @default.
- W4328124783 hasConceptScore W4328124783C62520636 @default.
- W4328124783 hasFunder F4320321001 @default.
- W4328124783 hasIssue "6" @default.
- W4328124783 hasLocation W43281247831 @default.
- W4328124783 hasOpenAccess W4328124783 @default.
- W4328124783 hasPrimaryLocation W43281247831 @default.
- W4328124783 hasRelatedWork W1574999717 @default.
- W4328124783 hasRelatedWork W166251047 @default.
- W4328124783 hasRelatedWork W2020564930 @default.
- W4328124783 hasRelatedWork W2059339452 @default.
- W4328124783 hasRelatedWork W2093556634 @default.
- W4328124783 hasRelatedWork W2262668847 @default.
- W4328124783 hasRelatedWork W2370766994 @default.
- W4328124783 hasRelatedWork W2794492057 @default.
- W4328124783 hasRelatedWork W2907097116 @default.
- W4328124783 hasRelatedWork W2995115364 @default.
- W4328124783 hasVolume "13" @default.
- W4328124783 isParatext "false" @default.
- W4328124783 isRetracted "false" @default.
- W4328124783 workType "article" @default.