# CFAT: Unleashing TriangularWindows for Image Super-resolution

arXiv: https://arxiv.org/abs/2403.16143 · HTML: https://mlsanity.com/paper/2403.16143/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 24 Mar 2024.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [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)
- [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)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [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)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [UniFormer: Unifying Convolution and Self-attention for Visual Recognition](https://mlsanity.com/paper/2201.09450/) (2022)
- [Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2108.11084/) (2021)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [Fast and Accurate Single Image Super-Resolution via Information Distillation Network](https://mlsanity.com/paper/1803.09454/) (2018)
- [Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution](https://mlsanity.com/paper/2003.07018/) (2020)
- [Accurate Image Restoration with Attention Retractable Transformer](https://mlsanity.com/paper/2210.01427/) (2022)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://mlsanity.com/paper/2209.11345/) (2022)
- [Deep Constrained Least Squares for Blind Image Super-Resolution](https://mlsanity.com/paper/2202.07508/) (2022)

## Built on by (most cited first, 11 of 11)

- [Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution](https://mlsanity.com/paper/2410.10140/) (2024)
- [MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation](https://mlsanity.com/paper/2509.21265/) (2025)
- [Sparse Reconstruction of Optical Doppler Tomography with Alternative State Space Model and Attention](https://mlsanity.com/paper/2404.17484/) (2024)
- [MatIR: A Hybrid Mamba-Transformer Image Restoration Model](https://mlsanity.com/paper/2501.18401/) (2025)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention](https://mlsanity.com/paper/2603.06738/) (2026)
- [IG-CFAT: An Improved GAN-Based Framework for Effectively Exploiting Transformers in Real-World Image Super-Resolution](https://mlsanity.com/paper/2406.13815/) (2024)
- [Sewer Image Super-Resolution with Depth Priors and Its Lightweight Network](https://mlsanity.com/paper/2407.19271/) (2024)
- [HSNet: Heterogeneous Subgraph Network for Single Image Super-resolution](https://mlsanity.com/paper/2510.06564/) (2025)
- [ASBA: A-line State Space Model and B-line Attention for Sparse Optical Doppler Tomography Reconstruction](https://mlsanity.com/paper/2601.14165/) (2026)
- [Dual-Branch State-Displacement Network for Sea Surface Temperature Super-Resolution](https://mlsanity.com/paper/2608.15423/) (2026)

## Abstract (arXiv)

Transformer-based models have revolutionized the field of image super-resolution (SR) by harnessing their inherent ability to capture complex contextual features. The overlapping rectangular shifted window technique used in transformer architecture nowadays is a common practice in super-resolution models to improve the quality and robustness of image upscaling. However, it suffers from distortion at the boundaries and has limited unique shifting modes. To overcome these weaknesses, we propose a non-overlapping triangular window technique that synchronously works with the rectangular one to mitigate boundary-level distortion and allows the model to access more unique sifting modes. In this paper, we propose a Composite Fusion Attention Transformer (CFAT) that incorporates triangular-rectangular window-based local attention with a channel-based global attention technique in image super-resolution. As a result, CFAT enables attention mechanisms to be activated on more image pixels and captures long-range, multi-scale features to improve SR performance. The extensive experimental results and ablation study demonstrate the effectiveness of CFAT in the SR domain. Our proposed model shows a significant 0.7 dB performance improvement over other state-of-the-art SR architectures.