# Multi-level Wavelet Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1907.03128 · HTML: https://mlsanity.com/paper/1907.03128/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2019.

## Built on by (most cited first, 30 of 59)

- [Wavelet Diffusion Models are fast and scalable Image Generators](https://mlsanity.com/paper/2211.16152/) (2022)
- [Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision](https://mlsanity.com/paper/2108.08119/) (2021)
- [MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network](https://mlsanity.com/paper/2304.01598/) (2023)
- [Fully Learnable Deep Wavelet Transform for Unsupervised Monitoring of High-Frequency Time Series](https://mlsanity.com/paper/2105.00899/) (2021)
- [Neural Fourier Filter Bank](https://mlsanity.com/paper/2212.01735/) (2022)
- [Wavelet Diffusion Neural Operator](https://mlsanity.com/paper/2412.04833/) (2024)
- [Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring](https://mlsanity.com/paper/2401.00027/) (2023)
- [HST: Hierarchical Swin Transformer for Compressed Image Super-resolution](https://mlsanity.com/paper/2208.09885/) (2022)
- [SWAGAN: A Style-based Wavelet-driven Generative Model](https://mlsanity.com/paper/2102.06108/) (2021)
- [Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review](https://mlsanity.com/paper/2308.00247/) (2023)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer](https://mlsanity.com/paper/2304.01627/) (2023)
- [WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement](https://mlsanity.com/paper/2212.08327/) (2022)
- [LiSnowNet: Real-time Snow Removal for LiDAR Point Cloud](https://mlsanity.com/paper/2211.10023/) (2022)
- [WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution](https://mlsanity.com/paper/2307.00430/) (2023)
- [Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild](https://mlsanity.com/paper/2203.10636/) (2022)
- [USIS: Unsupervised Semantic Image Synthesis](https://mlsanity.com/paper/2109.14715/) (2021)
- [ASCNet: Asymmetric Sampling Correction Network for Infrared Image Destriping](https://mlsanity.com/paper/2401.15578/) (2024)
- [Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks](https://mlsanity.com/paper/2110.04824/) (2021)
- [Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation](https://mlsanity.com/paper/2204.13873/) (2022)
- [The Power of Linear Combinations: Learning with Random Convolutions](https://mlsanity.com/paper/2301.11360/) (2023)
- [DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer](https://mlsanity.com/paper/2211.08577/) (2022)
- [Skip-WaveNet: A Wavelet based Multi-scale Architecture to Trace Snow Layers in Radar Echograms](https://mlsanity.com/paper/2310.19574/) (2023)
- [Multilayer deep feature extraction for visual texture recognition](https://mlsanity.com/paper/2208.10044/) (2022)
- [Wavelet-based Loss for High-frequency Interface Dynamics](https://mlsanity.com/paper/2209.02316/) (2022)
- [On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks](https://mlsanity.com/paper/2209.11740/) (2022)
- [Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets](https://mlsanity.com/paper/2303.06797/) (2023)
- [Wavelet-based Unsupervised Label-to-Image Translation](https://mlsanity.com/paper/2305.09647/) (2023)
- [Finger-UNet: A U-Net based Multi-Task Architecture for Deep Fingerprint Enhancement](https://mlsanity.com/paper/2310.00629/) (2023)
- [Window-based Channel Attention for Wavelet-enhanced Learned Image Compression](https://mlsanity.com/paper/2409.14090/) (2024)

## Abstract (arXiv)

In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further operations such as features extraction and analysis. Recently, dilated filter has been proposed to trade off between receptive field size and efficiency. But the accompanying gridding effect can cause a sparse sampling of input images with checkerboard patterns. To address this problem, in this paper, we propose a novel multi-level wavelet CNN (MWCNN) model to achieve better trade-off between receptive field size and computational efficiency. The core idea is to embed wavelet transform into CNN architecture to reduce the resolution of feature maps while at the same time, increasing receptive field. Specifically, MWCNN for image restoration is based on U-Net architecture, and inverse wavelet transform (IWT) is deployed to reconstruct the high resolution (HR) feature maps. The proposed MWCNN can also be viewed as an improvement of dilated filter and a generalization of average pooling, and can be applied to not only image restoration tasks, but also any CNNs requiring a pooling operation. The experimental results demonstrate effectiveness of the proposed MWCNN for tasks such as image denoising, single image super-resolution, JPEG image artifacts removal and object classification.