| <div align="center"> | |
| # [IEEE TIP] Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach | |
| [Gang Wu](https://scholar.google.com/citations?user=JSqb7QIAAAAJ), [Junjun Jiang](http://homepage.hit.edu.cn/jiangjunjun), [Junpeng Jiang](), and [Xianming Liu](http://homepage.hit.edu.cn/xmliu) | |
| [AIIA Lab](https://aiialabhit.github.io/team/), Harbin Institute of Technology. | |
| [](https://arxiv.org/abs/2401.05633)[](https://github.com/Aitical/CFSR) [](https://huggingface.co/GWu/CFSR/)[](https://drive.google.com/drive/folders/1M55TvlSn1BJVJ4Go5uVkvHFhfwo7Z5ov?usp=sharing)[](https://hits.sh/github.com/Aitical/CFSR/) | |
| </div> | |
| This repository is the official PyTorch implementation of "Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach" | |
| >Recent progress in single-image super-resolution (SISR) has achieved remarkable performance, yet the computational costs of these methods remain a challenge for deployment on resource-constrained devices. In particular, transformer-based methods, which leverage self-attention mechanisms, have led to significant breakthroughs but also introduce substantial computational costs. To tackle this issue, we introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR), offering an effective and efficient solution for lightweight image super-resolution. The proposed method inherits the advantages of both convolution-based and transformer-based approaches. Specifically, CFSR utilizes large kernel convolutions as a feature mixer to replace the self-attention module, efficiently modeling long-range dependencies and extensive receptive fields with minimal computational overhead. Furthermore, we propose an edge-preserving feed-forward network (EFN) designed to achieve local feature aggregation while effectively preserving high-frequency information. Extensive experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance compared to existing lightweight SR methods. When benchmarked against state-of-the-art methods such as ShuffleMixer, the proposed CFSR achieves a gain of 0.39 dB on the Urban100 dataset for the x2 super-resolution task while requiring 26\% and 31\% fewer parameters and FLOPs, respectively. | |
| ## Results | |
| Results of x2, x3, and x4 SR tasks are available at [Google Drive](https://drive.google.com/drive/folders/1M55TvlSn1BJVJ4Go5uVkvHFhfwo7Z5ov?usp=sharing) | |