Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace SSD with a learnt similarity metric initialised to SSD | atlas-based registration · UK Biobank brain MRI test split, subcortical structures | Dice score: 4.1 percentage points | Helped |
| replace LCC with a learnt similarity metric initialised to LCC | atlas-based registration · UK Biobank brain MRI test split, subcortical structures | Dice score: 0.6 percentage points | Helped |
| use the learnt similarity metric instead of SSD | VoxelMorph · UK Biobank brain MRI test split, subcortical structures | Dice score: 2.0 percentage points | Helped |
| use the learnt similarity metric instead of LCC | VoxelMorph · UK Biobank brain MRI test split, subcortical structures | Dice score: 1.5 percentage points | Helped |
| replace SSD with a learnt similarity metric initialised to SSD | atlas-based registration · UK Biobank brain MRI test split, subcortical structures | average surface distance: 0.1 mm | Helped |
| replace LCC with a learnt similarity metric initialised to LCC | atlas-based registration · UK Biobank brain MRI test split, subcortical structures | average surface distance: 0.01 mm | Helped |
| use the learnt similarity metric instead of SSD | VoxelMorph · UK Biobank brain MRI test split, subcortical structures | average surface distance: 0.06 mm | Helped |
| use the learnt similarity metric instead of LCC | VoxelMorph · UK Biobank brain MRI test split, subcortical structures | average surface distance: 0.06 mm | Helped |
| replace LCC with a learnt similarity metric initialised to LCC | atlas-based registration · UK Biobank brain MRI test split | non-diffeomorphic voxels: 0.00 (0.04) -> 0.00 (0.00) | Helped |
| replace the baseline similarity metric with the learnt metric | registration models · UK Biobank brain MRI test split | transformation smoothness | No clear effect |
Closest papers by meaning
- Learning Diffeomorphism for Medical Image Registration with Time-Embedded Architectures Using Semigroup Regularization (CVPR 2026 · similarity 0.87)
- Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance (NeurIPS 2026 · similarity 0.87)
- Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning With Pairwise Alignment (CVPR 2022 · similarity 0.87)
- Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging (ICLR 2025 · similarity 0.85)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.84)
- Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration (CVPR 2024 · similarity 0.84)
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.