A 2D Gaussian Splatting framework with MRI-specific anatomical priors, physics-constrained intensity modeling, and meta-learning domain adaptation achieves state-of-the-art MRI super-resolution while showing that intermediate input resolutions can outperform maximum-resolution inputs.
Medical image super-resolution reconstruction algorithms based on deep learning: A survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Real-ESRGAN delivers the best perceptual sharpness and edge detail at higher magnifications while SwinIR better preserves structural diagnostic features and SRCNN runs efficiently at low magnifications across multiple medical imaging domains.
citing papers explorer
-
PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution
A 2D Gaussian Splatting framework with MRI-specific anatomical priors, physics-constrained intensity modeling, and meta-learning domain adaptation achieves state-of-the-art MRI super-resolution while showing that intermediate input resolutions can outperform maximum-resolution inputs.
-
MedSR-Vision: Deep Learning Framework for Multi-Domain Medical Image Super-Resolution
Real-ESRGAN delivers the best perceptual sharpness and edge detail at higher magnifications while SwinIR better preserves structural diagnostic features and SRCNN runs efficiently at low magnifications across multiple medical imaging domains.