# One-Shot Image Restoration

arXiv: https://arxiv.org/abs/2404.17426 · HTML: https://mlsanity.com/paper/2404.17426/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 65 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [The Little Engine that Could: Regularization by Denoising (RED)](https://mlsanity.com/paper/1611.02862/) (2016)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks](https://mlsanity.com/paper/1805.12076/) (2018)
- [DeepRED: Deep Image Prior Powered by RED](https://mlsanity.com/paper/1903.10176/) (2019)
- [Ada-LISTA: Learned Solvers Adaptive to Varying Models](https://mlsanity.com/paper/2001.08456/) (2020)
- [Deep Internal Learning: Deep Learning from a Single Input](https://mlsanity.com/paper/2312.07425/) (2023)
- [Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network](https://mlsanity.com/paper/2201.11333/) (2022)
- [Recovery and Generalization in Over-Realized Dictionary Learning](https://mlsanity.com/paper/2006.06179/) (2020)
- [Convolutional Sparse Coding Fast Approximation with Application to Seismic Reflectivity Estimation](https://mlsanity.com/paper/2106.15296/) (2021)
- [Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets](https://mlsanity.com/paper/2209.14267/) (2022)
- [Domain-Aware Few-Shot Learning for Optical Coherence Tomography Noise Reduction](https://mlsanity.com/paper/2306.08102/) (2023)

## Built on by (most cited first, 3 of 3)

- [On Inverse Problems, Parameter Estimation, and Domain Generalization](https://mlsanity.com/paper/2506.06024/) (2025)
- [Information Theoretic Perspective on Representation Learning](https://mlsanity.com/paper/2601.11334/) (2026)
- [Hidden-Shot: Towards One-Shot Task Generalization for Low-Level Vision Generalist Models](https://mlsanity.com/paper/2607.01535/) (2026)

## Abstract (arXiv)

Image restoration, or inverse problems in image processing, has long been an extensively studied topic. In recent years supervised learning approaches have become a popular strategy attempting to tackle this task. Unfortunately, most supervised learning-based methods are highly demanding in terms of computational resources and training data (sample complexity). In addition, trained models are sensitive to domain changes, such as varying acquisition systems, signal sampling rates, resolution and contrast. In this work, we try to answer a fundamental question: Can supervised learning models generalize well solely by learning from one image or even part of an image? If so, then what is the minimal amount of patches required to achieve acceptable generalization? To this end, we focus on an efficient patch-based learning framework that requires a single image input-output pair for training. Experimental results demonstrate the applicability, robustness and computational efficiency of the proposed approach for supervised image deblurring and super-resolution. Our results showcase significant improvement of learning models' sample efficiency, generalization and time complexity, that can hopefully be leveraged for future real-time applications, and applied to other signals and modalities.