# ARM: Any-Time Super-Resolution Method

arXiv: https://arxiv.org/abs/2203.10812 · HTML: https://mlsanity.com/paper/2203.10812/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 21 Mar 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [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)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [Fourier Space Losses for Efficient Perceptual Image Super-Resolution](https://mlsanity.com/paper/2106.00783/) (2021)
- [Wide Activation for Efficient and Accurate Image Super-Resolution](https://mlsanity.com/paper/1808.08718/) (2018)
- [Learning with Privileged Information for Efficient Image Super-Resolution](https://mlsanity.com/paper/2007.07524/) (2020)
- [PAMS: Quantized Super-Resolution via Parameterized Max Scale](https://mlsanity.com/paper/2011.04212/) (2020)
- [Path-Restore: Learning Network Path Selection for Image Restoration](https://mlsanity.com/paper/1904.10343/) (2019)
- [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)
- [AdderSR: Towards Energy Efficient Image Super-Resolution](https://mlsanity.com/paper/2009.08891/) (2020)
- [Efficient Super Resolution Using Binarized Neural Network](https://mlsanity.com/paper/1812.06378/) (2018)
- [Journey Towards Tiny Perceptual Super-Resolution](https://mlsanity.com/paper/2007.04356/) (2020)
- [Towards Compact Single Image Super-Resolution via Contrastive Self-distillation](https://mlsanity.com/paper/2105.11683/) (2021)
- [Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms](https://mlsanity.com/paper/2105.03596/) (2021)
- [MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations](https://mlsanity.com/paper/2105.07085/) (2021)

## Built on by (most cited first, 19 of 19)

- [SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting](https://mlsanity.com/paper/2306.03110/) (2023)
- [CAMixerSR: Only Details Need More "Attention"](https://mlsanity.com/paper/2402.19289/) (2024)
- [CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input](https://mlsanity.com/paper/2304.06454/) (2023)
- [Real-Time Image Demoireing on Mobile Devices](https://mlsanity.com/paper/2302.02184/) (2023)
- [RefQSR: Reference-based Quantization for Image Super-Resolution Networks](https://mlsanity.com/paper/2404.01690/) (2024)
- [Accelerating Image Super-Resolution Networks with Pixel-Level Classification](https://mlsanity.com/paper/2407.21448/) (2024)
- [Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration](https://mlsanity.com/paper/2401.13221/) (2024)
- [Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues](https://mlsanity.com/paper/2409.14330/) (2024)
- [AnySR: Realizing Image Super-Resolution as Any-Scale, Any-Resource](https://mlsanity.com/paper/2407.04241/) (2024)
- [DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution](https://mlsanity.com/paper/2212.07613/) (2022)
- [Image super-resolution via dynamic network](https://mlsanity.com/paper/2310.10413/) (2023)
- [Efficient Image Super-Resolution via Symmetric Visual Attention Network](https://mlsanity.com/paper/2401.08913/) (2024)
- [Real-Time Neural-Enhancement for Online Cloud Gaming](https://mlsanity.com/paper/2501.06880/) (2025)
- [ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning](https://mlsanity.com/paper/2211.05488/) (2022)
- [ESSR: An 8K@30FPS Super-Resolution Accelerator With Edge Selective Network](https://mlsanity.com/paper/2503.20245/) (2025)
- [High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution](https://mlsanity.com/paper/2505.06975/) (2025)
- [Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution](https://mlsanity.com/paper/2510.01997/) (2025)
- [PixelSR: Efficient Screen Content Super-Resolution via Pixel Classification](https://mlsanity.com/paper/2608.00646/) (2026)
- [ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution](https://mlsanity.com/paper/2608.15349/) (2026)

## Abstract (arXiv)

This paper proposes an Any-time super-Resolution Method (ARM) to tackle the over-parameterized single image super-resolution (SISR) models. Our ARM is motivated by three observations: (1) The performance of different image patches varies with SISR networks of different sizes. (2) There is a tradeoff between computation overhead and performance of the reconstructed image. (3) Given an input image, its edge information can be an effective option to estimate its PSNR. Subsequently, we train an ARM supernet containing SISR subnets of different sizes to deal with image patches of various complexity. To that effect, we construct an Edge-to-PSNR lookup table that maps the edge score of an image patch to the PSNR performance for each subnet, together with a set of computation costs for the subnets. In the inference, the image patches are individually distributed to different subnets for a better computation-performance tradeoff. Moreover, each SISR subnet shares weights of the ARM supernet, thus no extra parameters are introduced. The setting of multiple subnets can well adapt the computational cost of SISR model to the dynamically available hardware resources, allowing the SISR task to be in service at any time. Extensive experiments on resolution datasets of different sizes with popular SISR networks as backbones verify the effectiveness and the versatility of our ARM. The source code is available at https://github.com/chenbong/ARM-Net.