Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-Resolution

• URL: http://arxiv.org/abs/2603.09621v1
• Date: Tue, 10 Mar 2026 13:00:42 GMT
• Title: Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-Resolution
• Abstract summary: High-resolution Magnetic Resonance Imaging (MRI) is vital for clinical diagnosis but limited by long acquisition times and motion artifacts.<n>Super-resolution (SR) reconstructs low-resolution scans into high-resolution images, yet existing methods are mutually constrained.<n>We propose a zero-shot MRI SR framework using explicit Gaussian representation to balance data requirements and efficiency.
• Score: 13.552352258334908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution [13.459705621719108]
  Magnetic resonance imaging (MRI) super-resolution is vital for improving diagnostic accessibility.<n>Most methods treat it as a deterministic mapping from a fixed low-resolution input to a high-resolution target.<n>We rethink MRI super-resolution as a physics-aware reconstruction problem, in which the goal is to identify the optimal resolution-SNR configuration.
  arXiv  Detail & Related papers  (2026-07-07T13:06:01Z)
• MRI2Qmap: multi-parametric quantitative mapping with MRI-driven denoising priors [0.0280162601599316]
  We introduce MRI2Qmap, a plug-and-play quantitative reconstruction framework.<n>It integrates the physical acquisition model with priors learned from deep denoising autoencoders pretrained on large multimodal weighted-MRI datasets.<n>The proposed method is validated on highly accelerated 3D whole-brain MRF data from both in-vivo and simulated acquisitions.
  arXiv  Detail & Related papers  (2026-03-11T21:23:52Z)
• M-Gaussian: An Magnetic Gaussian Framework for Efficient Multi-Stack MRI Reconstruction [8.108801952103073]
  We present M-Gaussian, adapting 3D Gaussian Splatting to MRI reconstruction.<n>On the FeTA dataset, M-Gaussian achieves 40.31 dB PSNR while being 14 times faster.
  arXiv  Detail & Related papers  (2026-02-24T12:57:34Z)
• Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstruction [30.203473273516895]
  Patch-based diffusion models have shown promise in learning effective data-driven priors over small real-valued datasets.<n>We show that PaDIS-MRI models trained on small datasets of as few as 25 k-space images outperform FastMRI-EDM on image quality metrics.
  arXiv  Detail & Related papers  (2025-09-25T20:18:56Z)
• ZECO: ZeroFusion Guided 3D MRI Conditional Generation [11.645873358288648]
  ZECO is a ZeroFusion guided 3D MRI conditional generation framework.<n>It extracts, compresses, and generates high-fidelity MRI images with corresponding 3D segmentation masks.<n>ZECO outperforms state-of-the-art models in both quantitative and qualitative evaluations on Brain MRI datasets.
  arXiv  Detail & Related papers  (2025-03-24T00:04:52Z)
• ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning [51.26601171361753]
  We propose ContextMRI, a text-conditioned diffusion model for MRI that integrates granular metadata into the reconstruction process.<n>We show that increasing the fidelity of metadata, ranging from slice location and contrast to patient age, sex, and pathology, systematically boosts reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-08T05:15:43Z)
• Towards General Text-guided Image Synthesis for Customized Multimodal Brain MRI Generation [51.28453192441364]
  Multimodal brain magnetic resonance (MR) imaging is indispensable in neuroscience and neurology. Current MR image synthesis approaches are typically trained on independent datasets for specific tasks. We present TUMSyn, a Text-guided Universal MR image Synthesis model, which can flexibly generate brain MR images.
  arXiv  Detail & Related papers  (2024-09-25T11:14:47Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• A Compact Implicit Neural Representation for Efficient Storage of Massive 4D Functional Magnetic Resonance Imaging [14.493622422645053]
  fMRI compressing poses unique challenges due to its intricate temporal dynamics, low signal-to-noise ratio, and complicated underlying redundancies. This paper reports a novel compression paradigm specifically tailored for fMRI data based on Implicit Neural Representation (INR)
  arXiv  Detail & Related papers  (2023-11-30T05:54:37Z)
• Volumetric Reconstruction Resolves Off-Resonance Artifacts in Static and Dynamic PROPELLER MRI [76.60362295758596]
  Off-resonance artifacts in magnetic resonance imaging (MRI) are visual distortions that occur when the actual resonant frequencies of spins within the imaging volume differ from the expected frequencies used to encode spatial information. We propose to resolve these artifacts by lifting the 2D MRI reconstruction problem to 3D, introducing an additional "spectral" dimension to model this off-resonance.
  arXiv  Detail & Related papers  (2023-11-22T05:44:51Z)
• A scan-specific unsupervised method for parallel MRI reconstruction via implicit neural representation [9.388253054229155]
  implicit neural representation (INR) has emerged as a new deep learning paradigm for learning the internal continuity of an object. The proposed method outperforms existing methods by suppressing the aliasing artifacts and noise. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.
  arXiv  Detail & Related papers  (2022-10-19T10:16:03Z)
• Negligible effect of brain MRI data preprocessing for tumor segmentation [36.89606202543839]
  We conduct experiments on three publicly available datasets and evaluate the effect of different preprocessing steps in deep neural networks. Our results demonstrate that most popular standardization steps add no value to the network performance. We suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization.
  arXiv  Detail & Related papers  (2022-04-11T17:29:36Z)
• Adaptive Gradient Balancing for UndersampledMRI Reconstruction and Image-to-Image Translation [60.663499381212425]
  We enhance the image quality by using a Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing technique. In MRI, our method minimizes artifacts, while maintaining a high-quality reconstruction that produces sharper images than other techniques.
  arXiv  Detail & Related papers  (2021-04-05T13:05:22Z)
• ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning [47.68307909984442]
  Single Image Super-Resolution (SISR) is a technique aimed to obtain high-resolution (HR) details from one single low-resolution input image. Deep learning extracts prior knowledge from big datasets and produces superior MRI images from the low-resolution counterparts.
  arXiv  Detail & Related papers  (2021-02-25T14:52:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.