PhyMRI-SR reframes MRI super-resolution as a physics-aware reconstruction problem rather than a deterministic mapping from one fixed low-resolution scan to a high-resolution target. The method adapts 2D Gaussian Splatting for resolution-agnostic, coordinate-based rendering and introduces anatomical and imaging-system priors, physics-constrained signal modeling, and meta-learning. It predicts proton density rho and effective relaxation rate R2, then synthesizes image intensities through physical equations. The paper reports state-of-the-art results on dynamic-resolution datasets and standard benchmarks, while detailed metrics and clinical validation are not included in the supplied abstract.
No heat snapshots are available in the last 24 hours.