# Cross-Modality Structural Guidance in 3D Latent Diffusion for Robust FLAIR Super-Resolution

arXiv: https://arxiv.org/abs/2606.25255 · HTML: https://mlsanity.com/paper/2606.25255/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 9 of 9)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Efficient Diffusion Model for Image Restoration by Residual Shifting](https://mlsanity.com/paper/2403.07319/) (2024)
- [A Modality-agnostic Multi-task Foundation Model for Human Brain Imaging](https://mlsanity.com/paper/2509.00549/) (2025)

## Abstract (arXiv)

High-resolution (HR) MRI acquisition is often hampered by scan time constraints, resulting in anisotropic or low-resolution scans (e.g., thick-slice FLAIR) that limit diagnostic accuracy. While deep learning-based super-resolution (SR) methods show promise, they often hallucinate anatomical details, which can compromise brain structural integrity. To mitigate this limitation, we introduce MR-DiffuSR, a Multi-Resolution Diffusion-based Super-Resolution framework that incorporates HR T1w structural image priors to guide the restoration of thick-slice FLAIR scans and operates in the 3D latent space. Our architecture introduces cross-modality structural swin attention, which derives structural attention maps from the HR T1w and applies them to the low-resolution FLAIR latent features. This design disentangles anatomical structure from modality-specific contrast, effectively preventing hallucinations. Furthermore, we employ a mixed-scale degradation strategy, training the model on a continuum of downsampling factors to ensure robustness to varying slice thicknesses, while optimizing with a DINOv3-based perceptual loss to preserve high-frequency semantic details. Evaluated on the ADNI-4 and ADNI-2 datasets, MR-DiffuSR surpasses both CNN and 2D diffusion approaches, achieving an average PSNR of 32.46 dB, SSIM of 0.97, and LPIPS of 0.07 across all downsampling factors. In downstream white matter hyperintensity segmentation, our model demonstrates exceptional robustness. While baseline performance collapses at 10x downsampling (Dice: 0.51), MR-DiffuSR maintains a Dice score of 0.63, preserving utility even at 7 mm equivalent slice thickness.