Research map / Image generation / Super-resolution
Spatio-Angular Convolutions for Super-resolution in Diffusion MRI
Matthew Lyon, Paul Armitage, Mauricio A Álvarez
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 b-vector coordinate embedding and spatial coordinates (PCCNN-Bv-Sp vs PCCNN) (ablation) | PCCNN · HCP single-shell dMRI q_in=10, b=3000 | angular error: 34.99 -> 33.53 | Improved |
| add b-vector embedding (PCCNN-Bv vs PCCNN) (ablation) | PCCNN · HCP single-shell dMRI q_in=6, b=1000 | angular error: 74.55 -> 73.55 | Improved |
| add spatial embedding (PCCNN-Sp vs PCCNN) (ablation) | PCCNN · HCP single-shell dMRI q_in=20, b=1000 | angular error: 44.03 -> 41.88 | Improved |
| add b-vector embedding (ablation) | PCCNN · HCP single-shell dMRI q_in=20, b=1000 | angular error: 44.03 -> 45.32 | Hurt |
| add spatial embedding (ablation) | PCCNN · HCP single-shell dMRI q_in=6, b=1000 | angular error: 74.55 -> 75.01 | Hurt |
| add b-vector embedding (ablation) | PCCNN · HCP multi-shell FBA q_in=20 | FOD ACC: 0.792 -> 0.807 | Improved |
| add b-vector embedding (ablation) | PCCNN · HCP multi-shell FBA q_in=6 | FOD ACC: 0.658 -> 0.681 | Improved |
| add b-vector embedding (ablation) | PCCNN · HCP multi-shell FBA q_in=20 | AFD AE: 0.068 -> 0.074 | Hurt |
| PCCNN (fewer params) vs RCNN single-shell dMRI | PCCNN · HCP single-shell dMRI q_in=20, b=3000 | angular error: 34.31 -> 24.86 | Improved |
| PCCNN vs RCNN at q_in=6, b=3000 | PCCNN · HCP single-shell dMRI | angular error: 52.11 -> 57.99 | Hurt |
| PCCNN vs low-res baseline in single-shell FBA at q_in=20 | PCCNN · HCP single-shell FBA | AFD AE: 0.048 -> 0.049 | No clear effect |
| PCCNN vs RCNN at q_in=20 single-shell FBA | PCCNN · HCP single-shell FBA | AFD AE: 0.065 -> 0.049 | Improved |
Closest papers by meaning
- A Steerable Deep Network for Model-Free Diffusion MRI Registration (NeurIPS 2026 · similarity 0.88)
- Equivariant spatio-hemispherical networks for diffusion MRI deconvolution (NeurIPS 2024 · similarity 0.88)
- Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution (CVPR 2024 · similarity 0.87)
- Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI (NeurIPS 2024 · similarity 0.86)
- Effective Diffusion Transformer Architecture for Image Super-Resolution (AAAI 2025 · similarity 0.85)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 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.
