# SFMformer: A Spatial-Frequency Modulation Transformer for Lightweight Image Super-Resolution

arXiv: https://arxiv.org/abs/2608.17966 · HTML: https://mlsanity.com/paper/2608.17966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [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)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [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)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary](https://mlsanity.com/paper/2401.08209/) (2024)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [Residual Local Feature Network for Efficient Super-Resolution](https://mlsanity.com/paper/2205.07514/) (2022)
- [Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2405.04964/) (2024)
- [N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.11436/) (2022)
- [HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution](https://mlsanity.com/paper/2407.05878/) (2024)
- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [Progressive Focused Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2503.20337/) (2025)
- [Dual-domain Modulation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.10047/) (2025)
- [PromptSR: Cascade Prompting for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2507.04118/) (2025)
- [Large Kernel Modulation Network for Efficient Image Super-Resolution](https://mlsanity.com/paper/2508.11893/) (2025)

## Abstract (arXiv)

Sparse attention mechanisms, which score all token pairs but propagate only the strongest, now underpin the most efficient Transformers for lightweight image super-resolution. This paper observes that sparsification changes what it means to improve such a network. A dense attention layer has one place where representation quality matters: the aggregation of attended features. A sparse layer has two, because the top-k operator first decides which tokens survive and only then decides what to do with them, and a token discarded at the selection stage cannot be recovered downstream. Selection quality and aggregation quality are therefore separable targets, addressed by modules placed before and after the attention respectively. We test this by pairing a dual-branch spatial enhancement on the input of a progressive focused attention with a wavelet-domain modulation on its output, forming SFMformer. Measuring each module alone and jointly over all fifteen benchmark-scale pairs, we find their gains are not additive: the joint gain exceeds the sum of the individual gains on nine pairs, and the sign of the discrepancy is predicted by how much the weaker module contributes on its own (r = -0.72), so the two compound when they relieve different constraints and overlap when they relieve the same one. Enabling spectral modulation once per block rather than once per layer retains the effect at roughly one-sixth of its cost, keeping the model below one million parameters at every scale. SFMformer ranks first on 28 of 30 PSNR/SSIM entries across five benchmarks and three upscaling factors. We report the cases where the pairing does not help, and deploy the model on a Raspberry Pi 5 to confirm the design is practical under tight resource budgets.