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,...
Saved in:
Main Authors: | Xu, Rui, Guo, Minghao, Wang, Jiaqi, Li, Xiaoxiao, Zhou, Bolei, Loy, Chen Change |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/160516 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Quantitative phase restoration in differential interference contrast (DIC) microscopy
by: Kou, S.S., et al.
Published: (2014) -
Noise matters in image restoration: from synthetic degradation to real-world challenges
by: Guo, Lanqing
Published: (2024) -
Simultaneous cartoon and texture Inpainting
by: Cai, J.-F., et al.
Published: (2014) -
Exploiting diffusion prior for real-world image super-resolution
by: Wang, Jianyi, et al.
Published: (2024) -
Image restoration via reconciliation of group sparsity and low-rank models
by: Zha, Zhiyuan, et al.
Published: (2022)