# edge-SR: Super-Resolution For The Masses arXiv: https://arxiv.org/abs/2108.10335 ยท HTML: https://mlsanity.com/paper/2108.10335/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Builds on 25 of its 46 references that are in the map. - First posted on arXiv 23 Aug 2021. ## Builds on (most cited first, 25 of 25) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016) - [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017) - [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017) - [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) - [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016) - [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) - [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015) - [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019) - [Maxout Networks](https://mlsanity.com/paper/1302.4389/) (2013) - [AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2009.06943/) (2020) - [Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report](https://mlsanity.com/paper/2105.07825/) (2021) - [Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices](https://mlsanity.com/paper/2105.10288/) (2021) - [MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors](https://mlsanity.com/paper/1908.07985/) (2019) - [Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2101.06658/) (2021) - [A Tour of Convolutional Networks Guided by Linear Interpreters](https://mlsanity.com/paper/1908.05168/) (2019) - [The Why, What and How of Artificial General Intelligence Chip Development](https://mlsanity.com/paper/2012.06338/) (2020) - [SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices](https://mlsanity.com/paper/2101.07996/) (2021) - [The Matrix Calculus You Need For Deep Learning](https://mlsanity.com/paper/1802.01528/) (2018) ## Built on by (most cited first, 9 of 9) - [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024) - [Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution](https://mlsanity.com/paper/2302.13800/) (2023) - [Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation](https://mlsanity.com/paper/2209.03355/) (2022) - [SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device](https://mlsanity.com/paper/2308.08137/) (2023) - [Multi-Depth Branch Network for Efficient Image Super-Resolution](https://mlsanity.com/paper/2309.17334/) (2023) - [Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images](https://mlsanity.com/paper/2210.04198/) (2022) - [MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation](https://mlsanity.com/paper/2502.14090/) (2025) - [ELSR: Extreme Low-Power Super Resolution Network For Mobile Devices](https://mlsanity.com/paper/2208.14600/) (2022) - [CIMGEN: Controlled Image Manipulation by Finetuning Pretrained Generative Models on Limited Data](https://mlsanity.com/paper/2401.13006/) (2024) ## Abstract (arXiv) Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On one hand, the current trend in Edge-AI chips shows a promising future in this direction, with rapid development of hardware that can run deep-learning tasks efficiently. On the other hand, in image SR only few architectures have pushed the limit to extreme small sizes that can actually run on edge devices at real-time. We explore possible solutions to this problem with the aim to fill the gap between classic upscalers and small deep learning configurations. As a transition from classic to deep-learning upscaling we propose edge-SR (eSR), a set of one-layer architectures that use interpretable mechanisms to upscale images. Certainly, a one-layer architecture cannot reach the quality of deep learning systems. Nevertheless, we find that for high speed requirements, eSR becomes better at trading-off image quality and runtime performance. Filling the gap between classic and deep-learning architectures for image upscaling is critical for massive adoption of this technology. It is equally important to have an interpretable system that can reveal the inner strategies to solve this problem and guide us to future improvements and better understanding of larger networks.