Heterogeneous Window Transformer for Image Denoising
- 5 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (11) , 6621-6632
Abstract
Deep networks can usually depend on extracting more structural information to improve denoising results. However, they may ignore correlation between pixels from an image to pursue better-denoising performance. Window Transformer can use long- and short-distance modeling to interact pixels to address mentioned problem. To make a tradeoff between distance modeling and denoising time, we propose a heterogeneous window Transformer (HWformer) for image denoising. HWformer first designs heterogeneous global windows to capture global context information for improving denoising effects. To build a bridge between long and short-distance modeling, global windows are horizontally and vertically shifted to facilitate diversified information without increasing denoising time. To prevent the information loss phenomenon of independent patches, sparse idea is guided a feed-forward network to extract local information of neighboring patches. The proposed HWformer only takes 30% of popular restoration Transformer in terms of denoising time. Its codes can be obtained at https://github.com/hellloxiaotian/HWformer .Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62201468)
- TCL science and technology innovation fund (D5140240118)
This publication has 54 references indexed in Scilit:
- A cross Transformer for image denoisingInformation Fusion, 2023
- A robust deformed convolutional neural network (CNN) for image denoisingCAAI Transactions on Intelligence Technology, 2022
- CycleISP: Real Image Restoration via Improved Data Synthesis2020
- Image denoising using deep CNN with batch renormalizationNeural Networks, 2020
- FOCNet: A Fractional Optimal Control Network for Image Denoising2019
- A High-Quality Denoising Dataset for Smartphone Cameras2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Learning Deep CNN Denoiser Prior for Image Restoration2017
- A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising2016
- The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observationsColor Research & Application, 2004