Abstract
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.
Abstract (translated)
高分辨率磁共振成像（MRI）对于临床诊断至关重要，但由于采集时间长和运动伪影的限制而受到制约。超分辨率（SR）技术可以将低分辨率扫描重建为高质量的高分辨率图像，但现有的方法在数据需求与效率之间存在着相互制约：基于配对数据的方法仅通过依赖昂贵且需精确对齐的数据集来实现高效性，而隐式的神经网络表示方法则避免了这样的数据需求，却牺牲了计算效率。我们提出了一种使用明确的高斯表示进行零样本MRI超分辨率重建框架，旨在平衡数据要求和效率之间的关系。 该框架中，针对MRI定制化的高斯参数嵌入了组织物理特性，减少了需要学习的参数数量，同时保持了磁共振信号的真实度。一种基于物理学原理的体积渲染策略通过归一化高斯聚合来模拟MRI信号形成过程。此外，还引入了一种基于砖块的与绘制顺序无关的光栅化方案，使得三维计算能够高度并行化，从而降低了训练和推理的成本。 在两个公开的MRI数据集上的实验表明，该方法具有卓越的重建质量和效率，展示了其应用于临床MRI超分辨率成像的巨大潜力。
URL
https://arxiv.org/abs/2603.09621
