# Fast Adaptation to Super-Resolution Networks via Meta-Learning

arXiv: https://arxiv.org/abs/2001.02905 · HTML: https://mlsanity.com/paper/2001.02905/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2020.

## Built on by (most cited first, 30 of 46)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution](https://mlsanity.com/paper/2108.05302/) (2021)
- [Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning](https://mlsanity.com/paper/2308.16481/) (2023)
- [Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution](https://mlsanity.com/paper/2203.07682/) (2022)
- [A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds](https://mlsanity.com/paper/2205.04910/) (2022)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction](https://mlsanity.com/paper/2310.19011/) (2023)
- [Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective](https://mlsanity.com/paper/2303.06859/) (2023)
- [Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation](https://mlsanity.com/paper/2108.08202/) (2021)
- [Meta-Learning based Degradation Representation for Blind Super-Resolution](https://mlsanity.com/paper/2207.13963/) (2022)
- [Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning](https://mlsanity.com/paper/2308.16484/) (2023)
- [Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions](https://mlsanity.com/paper/2106.03727/) (2021)
- [Deep Internal Learning: Deep Learning from a Single Input](https://mlsanity.com/paper/2312.07425/) (2023)
- [Efficient Meta-Tuning for Content-aware Neural Video Delivery](https://mlsanity.com/paper/2207.09691/) (2022)
- [Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations](https://mlsanity.com/paper/2104.03926/) (2021)
- [Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images](https://mlsanity.com/paper/2302.12491/) (2023)
- [MRI Super-Resolution with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2511.16854/) (2025)
- [Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution](https://mlsanity.com/paper/2103.15290/) (2021)
- [Meta Transferring for Deblurring](https://mlsanity.com/paper/2210.08036/) (2022)
- ["Zero-Shot" Point Cloud Upsampling](https://mlsanity.com/paper/2106.13765/) (2021)
- [MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces](https://mlsanity.com/paper/2309.08113/) (2023)
- [Restore from Restored: Single-image Inpainting](https://mlsanity.com/paper/2110.12822/) (2021)
- [SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution](https://mlsanity.com/paper/2111.15185/) (2021)
- [Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation](https://mlsanity.com/paper/2212.07886/) (2022)
- [Learning to Recover Spectral Reflectance from RGB Images](https://mlsanity.com/paper/2304.02162/) (2023)
- [Meta-Auxiliary Network for 3D GAN Inversion](https://mlsanity.com/paper/2305.10884/) (2023)
- [Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization](https://mlsanity.com/paper/2508.18859/) (2025)
- [Human and Scene Motion Deblurring using Pseudo-blur Synthesizer](https://mlsanity.com/paper/2111.12911/) (2021)

## Abstract (arXiv)

Conventional supervised super-resolution (SR) approaches are trained with massive external SR datasets but fail to exploit desirable properties of the given test image. On the other hand, self-supervised SR approaches utilize the internal information within a test image but suffer from computational complexity in run-time. In this work, we observe the opportunity for further improvement of the performance of SISR without changing the architecture of conventional SR networks by practically exploiting additional information given from the input image. In the training stage, we train the network via meta-learning; thus, the network can quickly adapt to any input image at test time. Then, in the test stage, parameters of this meta-learned network are rapidly fine-tuned with only a few iterations by only using the given low-resolution image. The adaptation at the test time takes full advantage of patch-recurrence property observed in natural images. Our method effectively handles unknown SR kernels and can be applied to any existing model. We demonstrate that the proposed model-agnostic approach consistently improves the performance of conventional SR networks on various benchmark SR datasets.