Research map / Image generation / Editing and style transfer
Breaking the Continuum: Discrete Distribution Learning for Structural MRI Reconstruction
Tianle Lyu, Mengjingcheng Mo, Ting Wen, Zhen Song, Zinan Xiong, Yanjie Zhu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| remove any one of coarse-to-fine, micro diffusion cycles or dual-domain scoring (ablation) | DiCoS · fastMRI knee 12-fold | PSNR (dB): 34.61, 32.58, 34.26 -> 35.32 | Improved |
| remove any one component (coarse-to-fine, MDC, DBS) (ablation) | DiCoS · fastMRI knee 12-fold | NMSE (%): 2.13, 2.87, 1.94 -> 1.43 | Improved |
| increase micro diffusion steps T beyond 3 (ablation) | DiCoS · fastMRI knee | PSNR | No clear effect |
| increase candidates K beyond 32 (ablation) | DiCoS · fastMRI knee | PSNR/SSIM | No clear effect |
| increase micro diffusion steps from T=1 to T=3 (ablation) | DiCoS · inference time | seconds: 2.88 -> 3.23 | Hurt |
| discrete-continuous synthesis vs continuous SelfRDB | DiCoS · fastMRI knee 12-fold | PSNR (dB): 33.87 -> 35.32 | Improved |
| DiCoS vs SelfRDB on SSIM | DiCoS · fastMRI brain 4-fold | SSIM (%): 89.65 -> 89.22 | Hurt |
| DiCoS vs SelfRDB on SSIM | DiCoS · fastMRI knee 4-fold | SSIM (%): 88.64 -> 87.88 | Hurt |
Closest papers by meaning
- Anatomical Consistency and Adaptive Prior-informed Transformation for Multi-contrast MR Image Synthesis via Diffusion Model (CVPR 2025 · similarity 0.86)
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.84)
- Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement (ICLR 2025 · similarity 0.84)
- Decompositional Neural Scene Reconstruction with Generative Diffusion Prior (CVPR 2025 · similarity 0.83)
- Null Space Matters: Range-Null Decomposition for Consistent Multi-Contrast MRI Reconstruction (AAAI 2024 · similarity 0.83)
- MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI (NeurIPS 2026 · similarity 0.83)
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.
