Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI

• URL: http://arxiv.org/abs/2605.02575v1
• Date: Mon, 04 May 2026 13:30:29 GMT
• Title: Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI
• Abstract summary: Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI)<n>We propose a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) that reconstructs high-resolution dMRI from a single view per diffusion direction.
• Score: 9.996806954463056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) that reconstructs high-resolution dMRI from a single view per diffusion direction, representing a massive acceleration. Our model, an MLP conditioned on a b=0 structural prior and the b-direction via FiLM, is trained end-to-end on the anisotropic input. The framework not only accurately reconstructs the trained b-directions (spatial SR) but also learns a continuous q-space representation, enabling high-fidelity "zero-shot" synthesis of unseen b-directions (angular SR). On simulated data, our method achieved high fidelity for both trained (34.82 dB) and unseen (33.08 dB) directions. Most importantly, the synthesized angular data also improved the quantitative accuracy of downstream DTI model fitting. Our SA-INR framework breaks the classical sampling limits, paving the way for fast, quantitative high-resolution dMRI.

Related papers

• MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution [50.60539317126614]
  MeanSR learns an LR-conditioned average velocity field to directly capture the finite-time transition from noisy inputs to plausible HR outputs.<n>Experiments show that MeanSR outperforms CTMSR on CLIPIQA, MUSIQ, and MANIQA while substantially reducing FLOPs and inference latency.
  arXiv  Detail & Related papers  (2026-08-10T10:33:18Z)
• High-fidelity 3D multi-slab diffusion MRI using Slab-shifting for Harmonized 3D Acquisition and Reconstruction with Profile Encoding Networks (SHARPEN) [6.762183349768633]
  Three-dimensional (3D) multi-slab imaging is a promising approach for high-resolution in vivo diffusion MRI (dMRI)<n>A major challenge, however, is slab boundary artifacts arising from non-ideal slab-selective RF excitation.<n>Non-rectangular slab profiles reduce signal intensity at slab boundaries, while profile overlap across adjacent slabs introduces inter-slab crosstalk.<n>We build on slab profile encoding and slab-shifting for Harmonized 3D Acquisition and Reconstruction with Profile Networks (SHARPEN)
  arXiv  Detail & Related papers  (2026-02-06T20:03:25Z)
• Unrolled Networks are Conditional Probability Flows in MRI Reconstruction [13.185194525641478]
  We introduce flow ODEs to MRI reconstruction by theoretically proving that unrolled networks are discrete implementations of conditional probability flow ODEs.<n>This connection provides explicit formulations for parameters and clarifies how intermediate states should evolve.<n>We propose Flow-Aligned Training (FLAT), which derives unrolled parameters from the ODE discretization and aligns intermediate reconstructions with the ideal ODE trajectory to improve stability and convergence.
  arXiv  Detail & Related papers  (2025-12-02T18:48:10Z)
• Physics-Guided Diffusion Transformer with Spherical Harmonic Posterior Sampling for High-Fidelity Angular Super-Resolution in Diffusion MRI [10.521817442478543]
  We introduce a Physics-Guided Diffusion Transformer (PGDiT) to explore physical priors throughout both training and inference stages.<n>During training, a Q-space Geometry-Aware Module (QGAM) with b-vector modulation and random angular masking facilitates direction-aware representation learning.<n>In inference, a two-stage Spherical Harmonics-Guided Posterior Sampling (SHPS) enforces alignment with the acquired data, followed by heat-diffusion-based regularization to ensure physically plausible reconstructions.
  arXiv  Detail & Related papers  (2025-09-07T04:31:58Z)
• MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers [12.639167101005695]
  Mean Reverting (MR) Diffusion directly modifies the structure of the differential equation (SDE)<n>Current training-free fast samplers are not directly applicable to MR Diffusion.<n>We propose a new algorithm named MaRS (MR Sampler) to reduce the sampling NFEs of MR Diffusion.
  arXiv  Detail & Related papers  (2025-02-11T14:57:33Z)
• Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCT [51.95884144860506]
  Ring artifacts are prevalent in 3D cone-beam computed tomography (CBCT)<n>Existing state-of-the-art (SOTA) ring artifact reduction (RAR) methods rely on supervised learning with large-scale paired CT datasets.<n>In this work, we propose Riner, a new unsupervised RAR method.
  arXiv  Detail & Related papers  (2024-12-08T08:22:58Z)
• Highly Accelerated MRI via Implicit Neural Representation Guided Posterior Sampling of Diffusion Models [2.5412006057370893]
  Implicit neural representation (INR) has emerged as a powerful paradigm for solving inverse problems. Our proposed framework can be a generalizable framework to solve inverse problems in other medical imaging tasks.
  arXiv  Detail & Related papers  (2024-07-03T01:37:56Z)
• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models [76.43625653814911]
  Diffusion models have gained popularity for accelerated MRI reconstruction due to their high sample quality. They can effectively serve as rich data priors while incorporating the forward model flexibly at inference time. We introduce SURE-based MRI Reconstruction with Diffusion models (SMRD) to enhance robustness during testing.
  arXiv  Detail & Related papers  (2023-10-03T05:05:35Z)
• Towards performant and reliable undersampled MR reconstruction via diffusion model sampling [67.73698021297022]
  DiffuseRecon is a novel diffusion model-based MR reconstruction method. It guides the generation process based on the observed signals. It does not require additional training on specific acceleration factors.
  arXiv  Detail & Related papers  (2022-03-08T02:25:38Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)

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.