Inpainting and restoration
Inpainting is a conservation process where damaged, deteriorating, or missing parts of an artwork are filled in to present a complete image
# Resources
- https://en.wikipedia.org/wiki/Inpainting
- https://paperswithcode.com/task/image-restoration
- https://www.nvidia.com/research/inpainting/
- An Introduction to Image Inpainting using Deep Learning
- GANs and Missing Data Imputation
# References
- #PAPER #REVIEW Image inpainting: A review (Elharrouss 2019)
# CNN-based
See AI/Computer Vision/Deep image prior
- #PAPER Feature Learning by Inpainting (Pathak 2016)
- #PAPER Image Inpainting for Irregular Holes Using Partial Convolutions (Liu 2018)
- #PAPER Partial Convolution based Padding (Liu 2018)
- #PAPER Probabilistic Semantic Inpainting with Pixel Constrained CNNs (Dupont 2019)
- #PAPER A Flexible Deep CNNs Framework for Image Restoration (2020)
- #PAPER Deep learning-Based 3D inpainting of brain MR images (Kwan Kang 2021)
# GAN-based
- #PAPER VIGAN: Missing View Imputation with Generative Adversarial Networks (Shang 2017)
- #PAPER Patch-Based Image Inpainting with GANs (Demir 2018)
- #PAPER GAIN: Missing Data Imputation using GANs (Yoon 2018)
- #PAPER MisGAN: Learning from Incomplete Data with Generative Adversarial Networks (Li 2019)
- #PAPER CollaGAN : Collaborative GAN for Missing Image Data Imputation (Li 2019)
- #PAPER DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting (Li 2020)
- #PAPER The image inpainting algorithm used on multi-scale generative adversarial networks and neighbourhood (Mo 2020)