DHTCUN: Deep Hybrid Transformer CNN U Network for Single-Image Super-Resolution
Open Access
- 26 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 122624-122641
Abstract
Recent advances in image super-resolution have investigated various transformer and CNN techniques to improve quantitative and perceptual outcomes. Reconstructing high-resolution images from their low-resolution equivalents by combining the power of transformers and CNN has been a crucial task in recent times.We propose a novel U-shaped architecture that integrates transformers and convolutional neural networks (CNNs) to leverage the strengths of both approaches. The network incorporates a novel Parallel Hybrid Transformer CNN Block (PHTCB) on the backbone of the U-shaped design, ensuring computational efficiency and robust hierarchical feature representation. Our architecture incorporates triple-enhanced spatial-attention mechanisms and a Transformer CNN (TCN) Block in PHTCB. The TCN Block helps preserve sharp edges and intricate details often lost in traditional SISR methods and enhances the visual fidelity of the reconstructed high-resolution images. Additionally, we introduce the triple-enhanced spatial attention (TESA) approach that helps precisely localize of important features. Blurring can be reduced for crucial features by focusing on these critical areas because of the network’s ability to control features at various scales. Experiments demonstrate that our proposed method yields better quantitative measurements, including visually appealing high-resolution image reconstructions, peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM).Keywords
Funding Information
- the Ratchadapiseksompotch Fund, Chulalongkorn University
- The Second Century Fund (C2F), Chulalongkorn University
This publication has 54 references indexed in Scilit:
- Single Image Super-Resolution Via Residual Neuron Attention Networks2020
- Deep Learning Algorithm for Satellite Imaging Based Cyclone DetectionIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020
- Denoising convolutional neural network with mask for salt and pepper noiseIET Image Processing, 2019
- FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image DenoisingIEEE Transactions on Image Processing, 2018
- Sketch-based manga retrieval using manga109 datasetMultimedia Tools and Applications, 2016
- Accelerating the Super-Resolution Convolutional Neural Network2016
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Weighted Nuclear Norm Minimization with Application to Image Denoising2014
- A super-resolution reconstruction algorithm for surveillance imagesSignal Processing, 2010
- Super-Resolution in Medical ImagingThe Computer Journal, 2008