# ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution

arXiv: https://arxiv.org/abs/2608.15349 · HTML: https://mlsanity.com/paper/2608.15349/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [Wide Activation for Efficient and Accurate Image Super-Resolution](https://mlsanity.com/paper/1808.08718/) (2018)
- [Learning Frequency-aware Dynamic Network for Efficient Super-Resolution](https://mlsanity.com/paper/2103.08357/) (2021)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [CAMixerSR: Only Details Need More "Attention"](https://mlsanity.com/paper/2402.19289/) (2024)
- [Journey Towards Tiny Perceptual Super-Resolution](https://mlsanity.com/paper/2007.04356/) (2020)
- [ARM: Any-Time Super-Resolution Method](https://mlsanity.com/paper/2203.10812/) (2022)
- [Adaptive Patch Exiting for Scalable Single Image Super-Resolution](https://mlsanity.com/paper/2203.11589/) (2022)
- [FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline](https://mlsanity.com/paper/2312.11537/) (2023)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Functional Neural Networks for Parametric Image Restoration Problems](https://mlsanity.com/paper/2111.00361/) (2021)

## Abstract (arXiv)

To accelerate single image super-resolution (SISR) networks on large images (2K-8K), many recent approaches decompose an image into small patches and dynamically determine an execution path according to its difficulty (referred to as a dynamic network). To quantify the hardness of a patch, they mainly rely on a handcrafted assessment score, e.g., edge, which weakly associates a patch's texture with the computational complexity of a SISR model. To address the problem, we introduce ENAF - a dynamic network for SISR with an adaptive patch fusion. Built on top of a backbone, ENAF incorporates multiple early exits (EEs) to tackle the over-parameterized SISR model. More importantly, ENAF plugs a tiny network that estimates PSNR to associate data texture with a computation cost at an EE. Based on the scores, ENAF effectively assigns image patches to an exit, enhancing the quality-complexity trade-off. Extensive experiments on common datasets with popular SISR backbones demonstrate the effectiveness of ENAF in various settings. The source code is provided in https://github.com/nmduonggg/ENAF