Image restoration in frequency space using complex-valued CNNs
Open Access
- 23 September 2024
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 7, 1353873
Abstract
Real-valued convolutional neural networks (RV-CNNs) in the spatial domain have outperformed classical approaches in many image restoration tasks such as image denoising and super-resolution. Fourier analysis of the results produced by these spatial domain models reveals the limitations of these models in properly processing the full frequency spectrum. This lack of complete spectral information can result in missing textural and structural elements. To address this limitation, we explore the potential of complex-valued convolutional neural networks (CV-CNNs) for image restoration tasks. CV-CNNs have shown remarkable performance in tasks such as image classification and segmentation. However, CV-CNNs for image restoration problems in the frequency domain have not been fully investigated to address the aforementioned issues. Here, we propose several novel CV-CNN-based models equipped with complex-valued attention gates for image denoising and super-resolution in the frequency domains. We also show that our CV-CNN-based models outperform their real-valued counterparts for denoising super-resolution structured illumination microscopy (SR-SIM) and conventional image datasets. Furthermore, the experimental results show that our proposed CV-CNN-based models preserve the frequency spectrum better than their real-valued counterparts in the denoising task. Based on these findings, we conclude that CV-CNN-based methods provide a plausible and beneficial deep learning approach for image restoration in the frequency domain.Keywords
This publication has 58 references indexed in Scilit:
- Biologically inspired image invariance guided illuminant estimation using shallow and deep modelsExpert Systems with Applications, 2024
- Uncertainty-guided hierarchical frequency domain Transformer for image restorationKnowledge-Based Systems, 2023
- Comparison Between Equivalent Architectures of Complex-valued and Real-valued Neural Networks - Application on Polarimetric SAR Image SegmentationJournal of Signal Processing Systems, 2022
- A novel complex-valued convolutional neural network for medical image denoisingBiomedical Signal Processing and Control, 2021
- Image denoising using complex-valued deep CNNPattern Recognition, 2021
- Detail retaining convolutional neural network for image denoisingJournal of Visual Communication and Image Representation, 2020
- Complex Fully Convolutional Neural Networks for MR Image Reconstruction2018
- Convolutional Neural Networks for Image Denoising and Restoration2018
- Classification of Skeletal Wireframe Representation of Hand Gesture Using Complex-Valued Neural NetworkNeural Processing Letters, 2014
- Statistical Signal Processing of Complex-Valued Data2010