Research map / Image generation / Super-resolution
MiCo: Microstructure-Consistent Flow Matching for Diffusion MRI Angular Super-Resolution
Zhixuan Zhou, Tingting Dan, Guorong Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes MiCo, a physics-guided flow matching framework for diffusion MRI angular super-resolution that recovers dense q-space signals from sparse acquisitions.
Problem
Long diffusion-weighted MRI scan times, caused by densely sampling q-space across many directions and shells, limit clinical use; angular super-resolution aims to recover dense signal from sparse acquisitions.
Approach
Uses the cumulant expansion fact that the diffusion signal's log is approximately polynomial in the b-value/angular structure to guide a flow matching generative model toward microstructure-consistent reconstructions (abstract truncated; details beyond the abstract are not available).
Experimental setup
Builds on: flow matching cumulant expansion
Closest papers by meaning
- Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution (CVPR 2024 · similarity 0.88)
- A Steerable Deep Network for Model-Free Diffusion MRI Registration (NeurIPS 2026 · similarity 0.86)
- Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement (ICLR 2025 · similarity 0.86)
- Anatomical Consistency and Adaptive Prior-informed Transformation for Multi-contrast MR Image Synthesis via Diffusion Model (CVPR 2025 · similarity 0.86)
- Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching (CVPR 2024 · similarity 0.85)
- One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
