Research map / 3D vision / 3D generation
Unified Multi-plane Autoregressive Diffusion for 3D Multi-Contrast MRI Synthesis
Yejee Shin, Geonhui Son, Jinglu Wang, Minwoo Jung, Yan Lu, Dosik Hwang
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 |
|---|---|---|---|
| add autoregressive synthesis with g=1 (ablation) | MPAD · ADNI avg PSNR | PSNR: 22.79 -> 22.87 | Improved |
| add autoregressive synthesis with g=1 (ablation) | MPAD · IXI avg PSNR | PSNR: 28.89 -> 29.14 | Improved |
| use 3D instead of 2D conditioning encoder (ablation) | MPAD · ADNI avg | PSNR: +0.72 | Improved |
| use 3D instead of 2D conditioning encoder (ablation) | MPAD · IXI avg | PSNR: +1.19 | Improved |
| Gaussian noise masking instead of learnable mask token (ablation) | MPAD · ADNI avg | PSNR: +0.32 | Improved |
| Gaussian noise masking instead of learnable mask token (ablation) | MPAD · IXI avg | PSNR: +2.00 | Improved |
| add inter-plane priors (ablation) | MPAD · ADNI avg | PSNR: +1.12 | Improved |
| add inter-plane priors (ablation) | MPAD · IXI avg | PSNR: +1.88 | Improved |
| add sagittal plane to coronal-only generation (ablation) | MPAD · ADNI avg | PSNR: 22.82 -> 23.32 | Improved |
| add sagittal plane to coronal-only generation (ablation) | MPAD · IXI avg | PSNR: 29.17 -> 29.00 | Hurt |
| add refinement pass on first plane (ablation) | MPAD · ADNI avg | PSNR: 23.49 -> 23.54 | Improved |
| add refinement pass on first plane (ablation) | MPAD · IXI avg | PSNR: 29.29 -> 29.37 | Improved |
Closest papers by meaning
- Anatomical Consistency and Adaptive Prior-informed Transformation for Multi-contrast MR Image Synthesis via Diffusion Model (CVPR 2025 · similarity 0.89)
- Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI (NeurIPS 2024 · similarity 0.88)
- AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation (NeurIPS 2026 · similarity 0.86)
- Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution (CVPR 2024 · similarity 0.86)
- Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning (CVPR 2024 · similarity 0.86)
- Denoising Diffusion via Image-Based Rendering (ICLR 2024 · 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.
