# Restore from Restored: Single-image Inpainting

arXiv: https://arxiv.org/abs/2102.08078 · HTML: https://mlsanity.com/paper/2102.08078/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 16 Feb 2021.

## Builds on (most cited first, 26 of 26)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [One weird trick for parallelizing convolutional neural networks](https://mlsanity.com/paper/1404.5997/) (2014)
- [View Synthesis by Appearance Flow](https://mlsanity.com/paper/1605.03557/) (2016)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://mlsanity.com/paper/1908.03852/) (2019)
- [Deep Video Inpainting](https://mlsanity.com/paper/1905.01639/) (2019)
- [Recurrent Feature Reasoning for Image Inpainting](https://mlsanity.com/paper/2008.03737/) (2020)
- [Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting](https://mlsanity.com/paper/1904.07475/) (2019)
- [Foreground-aware Image Inpainting](https://mlsanity.com/paper/1901.05945/) (2019)
- [Image Inpainting via Generative Multi-column Convolutional Neural Networks](https://mlsanity.com/paper/1810.08771/) (2018)
- [Fast Adaptation to Super-Resolution Networks via Meta-Learning](https://mlsanity.com/paper/2001.02905/) (2020)
- [Video Inpainting of Complex Scenes](https://mlsanity.com/paper/1503.05528/) (2015)
- [Restore from Restored: Single Image Denoising with Pseudo Clean Image](https://mlsanity.com/paper/2003.04721/) (2020)

## Abstract (arXiv)

Recent image inpainting methods show promising results due to the power of deep learning, which can explore external information available from a large training dataset. However, many state-of-the-art inpainting networks are still limited in exploiting internal information available in the given input image at test time. To mitigate this problem, we present a novel and efficient self-supervised fine-tuning algorithm that can adapt the parameters of fully pre-trained inpainting networks without using ground-truth target images. We update the parameters of the pre-trained state-of-the-art inpainting networks by utilizing existing self-similar patches within the given input image without changing network architecture and improve the inpainting quality by a large margin. Qualitative and quantitative experimental results demonstrate the superiority of the proposed algorithm, and we achieve state-of-the-art inpainting results on publicly available numerous benchmark datasets.