PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution

Hugging Face Daily Papers Papers
physics-aware mri super-resolution gaussian-splatting meta-learning medical-imaging

Summary

This paper proposes PhyMRI-SR, a physics-aware MRI super-resolution method that uses Gaussian splatting and physics-constrained modeling to dynamically adapt resolution-SNR configurations, achieving state-of-the-art performance.

Magnetic resonance imaging (MRI) super-resolution is vital for improving diagnostic accessibility, yet most methods treat it as a deterministic mapping from a fixed low-resolution input to a high-resolution target. This overlooks a key property of MRI acquisition physics: spatial resolution and signal-to-noise ratio (SNR) are inherently coupled, making any given low-resolution scan merely one of many possible realizations under varying acquisition trade-offs. We rethink MRI super-resolution as a physics-aware reconstruction problem, in which the goal is to identify the optimal resolution-SNR configuration and then super-resolve it to obtain high-quality MRI results. A key implication of this formulation is that MRI resolution becomes dynamic rather than fixed. To handle such resolution-heterogeneous inputs, we adapt 2D Gaussian Splatting (2D GS) to MRI by formulating reconstruction as a coordinate-based, resolution-agnostic rendering problem. To further enhance fidelity, we introduce three innovations: (1) a prior-aware Gaussian representation that combines an Anatomical Structure Prior for tissue-specific kernel initialization with an Imaging System Prior that captures hardware characteristics via a covariance dictionary; (2) a physics-constrained signal modeling scheme that predicts intrinsic tissue parameters (proton density rho and effective relaxation rate R2) and synthesizes intensities through governing physical equations, ensuring biophysically plausible contrast; and (3) a meta-learning framework that alleviates paired-data scarcity by pretraining on simulated data and adapting to real-world conditions. Extensive experiments on dynamic-resolution datasets and standard benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting its strong potential for clinical deployment.
Original Article
View Cached Full Text

Cached at: 07/10/26, 06:16 AM

Paper page - PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution

Source: https://huggingface.co/papers/2607.06238

Abstract

MR super-resolution is reformulated as a physics-aware reconstruction problem that dynamically adapts resolution-SNR configurations using Gaussian splatting with prior-aware representations and physics-constrained modeling.

Magnetic resonance imaging (MRI) super-resolution is vital for improving diagnostic accessibility, yet most methods treat it as a deterministic mapping from a fixed low-resolution input to a high-resolution target. This overlooks a key property of MRI acquisition physics: spatial resolution and signal-to-noise ratio (SNR) are inherently coupled, making any given low-resolution scan merely one of many possible realizations under varying acquisition trade-offs. We rethink MRI super-resolution as a physics-aware reconstruction problem, in which the goal is to identify the optimal resolution-SNR configuration and then super-resolve it to obtain high-quality MRI results. A key implication of this formulation is that MRI resolution becomes dynamic rather than fixed. To handle such resolution-heterogeneous inputs, we adapt 2DGaussian Splatting(2D GS) to MRI by formulating reconstruction as a coordinate-based, resolution-agnostic rendering problem. To further enhance fidelity, we introduce three innovations: (1) a prior-aware Gaussian representation that combines anAnatomical Structure Priorfor tissue-specific kernel initialization with anImaging System Priorthat captures hardware characteristics via a covariance dictionary; (2) a physics-constrained signal modeling scheme that predicts intrinsic tissue parameters (proton densityrho andeffective relaxation rateR2) and synthesizes intensities through governing physical equations, ensuringbiophysically plausible contrast; and (3) ameta-learningframework that alleviates paired-data scarcity by pretraining onsimulated dataand adapting to real-world conditions. Extensive experiments on dynamic-resolution datasets and standard benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting its strong potential for clinical deployment.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2607\.06238

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.06238 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.06238 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.06238 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement

Hugging Face Daily Papers

This paper introduces a new task, reference-guided generated content super-resolution-refinement (RefGC-SR²), which simultaneously recovers high-resolution details and refines generative artifacts using a frequency-aware diffusion transformer model. The method leverages a high-resolution reference image to improve the quality of AI-generated images during post-processing.