TL;DR
The proposed MSGF-Net embeds a Hybrid Gradient-Frequency Attention Module (HG-FAM) within the residual bottlenecks to achieve dual-domain synergistic perception of global spectral energy and spatial gradient details and significantly outperforms existing main-stream methodologies.
Experiments demonstrate that SCGF-GAN effectively suppresses complex artifacts while preserving fine structural details, outperforming existing methods in both quantitative metrics and perceptual image quality.
The experimental results demonstrate that MHSG-Model has a good performance on preserving detail information and removing artifacts, which show the potential to be applied in clinical sparse view spectral CT reconstruction.
A two-stage framework integrating degradation-aware self-supervised contrastive pre-training with frequency-spatial domain feature learning is proposed, offering a reliable solution for NR-IQA in real-world multimedia systems and advancing the alignment between computational quality assessment and human visual percepti...
DLIR combined with high-frequency kernels reduced image noise while preserving spatial resolution and FBP-like noise texture, outperforming IR in detectability for most lesion sizes, concentrations, and dose levels.
A Multi-Feature Guided Progressive Divide-and-Conquer reconstruction network that achieves synergistic optimization through three novel modules provides an accurate and efficient solution for clinical rapid MRI scanning, demonstrating significant potential for clinical translation.
An AI-based convolutional auto-encoder model is presented to resolve the low dose CT image denoising and quality improvement of paired Quarter Dose CT data and Full Dose CT data, suggesting that the suggested framework is useful to reduce the low-dose CT noise and maintain the structural similarity simultaneously.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
