Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-Resolution
This work addresses the challenge of high-resolution MRI for clinical diagnosis by offering a more efficient and data-light super-resolution method, though it appears incremental as it builds on existing Gaussian representation techniques.
The paper tackles the problem of MRI super-resolution by proposing a zero-shot framework that balances data requirements and computational efficiency, achieving superior reconstruction quality and efficiency on two public datasets.
High-resolution Magnetic Resonance Imaging (MRI) is vital for clinical diagnosis but limited by long acquisition times and motion artifacts. Super-resolution (SR) reconstructs low-resolution scans into high-resolution images, yet existing methods are mutually constrained: paired-data methods achieve efficiency only by relying on costly aligned datasets, while implicit neural representation approaches avoid such data needs at the expense of heavy computation. We propose a zero-shot MRI SR framework using explicit Gaussian representation to balance data requirements and efficiency. MRI-tailored Gaussian parameters embed tissue physical properties, reducing learnable parameters while preserving MR signal fidelity. A physics-grounded volume rendering strategy models MRI signal formation via normalized Gaussian aggregation. Additionally, a brick-based order-independent rasterization scheme enables highly parallel 3D computation, lowering training and inference costs. Experiments on two public MRI datasets show superior reconstruction quality and efficiency, demonstrating the method's potential for clinical MRI SR.