# WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution

arXiv: https://arxiv.org/abs/2307.00430 · HTML: https://mlsanity.com/paper/2307.00430/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 1 Jul 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (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)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Improving Generalization Performance by Switching from Adam to SGD](https://mlsanity.com/paper/1712.07628/) (2017)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [On Efficient Transformer-Based Image Pre-training for Low-Level Vision](https://mlsanity.com/paper/2112.10175/) (2021)
- [Multi-level Wavelet Convolutional Neural Networks](https://mlsanity.com/paper/1907.03128/) (2019)
- [WaveMix: A Resource-efficient Neural Network for Image Analysis](https://mlsanity.com/paper/2205.14375/) (2022)
- [Convolutional Xformers for Vision](https://mlsanity.com/paper/2201.10271/) (2022)

## Built on by (most cited first, 10 of 10)

- [MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution](https://mlsanity.com/paper/2404.09571/) (2024)
- [HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution](https://mlsanity.com/paper/2412.03748/) (2024)
- [Dual-domain Modulation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.10047/) (2025)
- [GestFormer: Multiscale Wavelet Pooling Transformer Network for Dynamic Hand Gesture Recognition](https://mlsanity.com/paper/2405.11180/) (2024)
- [Low-Resource Video Super-Resolution using Memory, Wavelets, and Deformable Convolutions](https://mlsanity.com/paper/2502.01816/) (2025)
- [ConvMixFormer- A Resource-efficient Convolution Mixer for Transformer-based Dynamic Hand Gesture Recognition](https://mlsanity.com/paper/2411.07118/) (2024)
- [FIPER: Factorized Features for Robust Image Super-Resolution and Compression](https://mlsanity.com/paper/2410.18083/) (2024)
- [Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolution](https://mlsanity.com/paper/2511.01175/) (2025)
- [WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency](https://mlsanity.com/paper/2409.10582/) (2024)
- [Fourier-Guided Attention Upsampling for Image Super-Resolution](https://mlsanity.com/paper/2508.10616/) (2025)

## Abstract (arXiv)

Image super-resolution research recently been dominated by transformer models which need higher computational resources than CNNs due to the quadratic complexity of self-attention. We propose a new neural network -- WaveMixSR -- for image super-resolution based on WaveMix architecture which uses a 2D-discrete wavelet transform for spatial token-mixing. Unlike transformer-based models, WaveMixSR does not unroll the image as a sequence of pixels/patches. It uses the inductive bias of convolutions along with the lossless token-mixing property of wavelet transform to achieve higher performance while requiring fewer resources and training data. We compare the performance of our network with other state-of-the-art methods for image super-resolution. Our experiments show that WaveMixSR achieves competitive performance in all datasets and reaches state-of-the-art performance in the BSD100 dataset on multiple super-resolution tasks. Our model is able to achieve this performance using less training data and computational resources while maintaining high parameter efficiency compared to current state-of-the-art models.