Texture memory-augmented deep patch-based image inpainting
Patch-based methods and deep networks have been employed to tackle image inpainting problem, with their own strengths and weaknesses. Patch-based methods are capable of restoring a missing region with high-quality texture through searching nearest neighbor patches from the unmasked regions. However,...
Principais autores: | Xu, Rui, Guo, Minghao, Wang, Jiaqi, Li, Xiaoxiao, Zhou, Bolei, Loy, Chen Change |
---|---|
Outros Autores: | School of Computer Science and Engineering |
Formato: | Journal Article |
Idioma: | English |
Publicado em: |
2022
|
Assuntos: | |
Acesso em linha: | https://hdl.handle.net/10356/160516 |
Registros relacionados
-
Inpainting with style: forcing style coherence to image inpainting with deep image prior
por: Elena Morotti, et al.
Publicado em: (2024-11-01) -
Foggy image restoration using deep sub‐pixel reconstruction network
por: Linge Li, et al.
Publicado em: (2024-02-01) -
An Integration Framework for the Inpainting and Colorization of Arbitrary Masked Grayscale Images
por: Woon-Ha Yeo, et al.
Publicado em: (2025-02-01) -
Inpainting of damaged temple murals using edge- and line-guided diffusion patch GAN
por: G. Sumathi, et al.
Publicado em: (2024-11-01) -
Image inpainting network based on multi‐level attention mechanism
por: Hongyue Xiang, et al.
Publicado em: (2024-02-01)