# Single image super-resolution based on trainable feature matching attention network

arXiv: https://arxiv.org/abs/2405.18872 · HTML: https://mlsanity.com/paper/2405.18872/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 25 of 25)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [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)
- [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)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [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)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [Feedback Network for Image Super-Resolution](https://mlsanity.com/paper/1903.09814/) (2019)
- [Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks](https://mlsanity.com/paper/1710.01992/) (2017)
- [Densely Residual Laplacian Super-Resolution](https://mlsanity.com/paper/1906.12021/) (2019)
- [Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution](https://mlsanity.com/paper/1809.11130/) (2018)
- [Single Image Super-Resolution via Cascaded Multi-Scale Cross Network](https://mlsanity.com/paper/1802.08808/) (2018)

## Built on by (most cited first, 4 of 4)

- [Learning Accurate and Enriched Features for Stereo Image Super-Resolution](https://mlsanity.com/paper/2406.16001/) (2024)
- [QUIET-SR: Quantum Image Enhancement Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2503.08759/) (2025)
- [Towards Arbitrary-Scale Spacecraft Image Super-Resolution via Salient Region-Guidance](https://mlsanity.com/paper/2504.18127/) (2025)
- [Efficient Feedback Gate Network for Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2506.17361/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have been widely employed for image Super-Resolution (SR) in recent years. Various techniques enhance SR performance by altering CNN structures or incorporating improved self-attention mechanisms. Interestingly, these advancements share a common trait. Instead of explicitly learning high-frequency details, they learn an implicit feature processing mode that utilizes weighted sums of a feature map's own elements for reconstruction, akin to convolution and non-local. In contrast, early dictionary-based approaches learn feature decompositions explicitly to match and rebuild Low-Resolution (LR) features. Building on this analysis, we introduce Trainable Feature Matching (TFM) to amalgamate this explicit feature learning into CNNs, augmenting their representation capabilities. Within TFM, trainable feature sets are integrated to explicitly learn features from training images through feature matching. Furthermore, we integrate non-local and channel attention into our proposed Trainable Feature Matching Attention Network (TFMAN) to further enhance SR performance. To alleviate the computational demands of non-local operations, we propose a streamlined variant called Same-size-divided Region-level Non-Local (SRNL). SRNL conducts non-local computations in parallel on blocks uniformly divided from the input feature map. The efficacy of TFM and SRNL is validated through ablation studies and module explorations. We employ a recurrent convolutional network as the backbone of our TFMAN to optimize parameter utilization. Comprehensive experiments on benchmark datasets demonstrate that TFMAN achieves superior results in most comparisons while using fewer parameters. The code is available at https://github.com/qizhou000/tfman.