Research map / 3D vision / Face and shape
Graph-Based Slice-to-Volume Deformable Registration
Enzo Ferrante, Nikos Paragios A
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 |
|---|---|---|---|
| decouple label space into deformation and plane-position subgraphs instead of overparameterized 5D labels | slice-to-volume graph registration · Heart MRI dataset (monomodal, SAD) | rigid error, DICE, Hausdorff, CMD, running time | Improved |
| use high-order third-order cliques instead of decoupled pairwise model | slice-to-volume graph registration · Brain US-MRI dataset (multimodal, MI) | segmentation statistics (DICE etc.) | Improved |
| use decoupled model instead of high-order model | slice-to-volume graph registration · Brain US-MRI dataset (multimodal, MI) | computational time | Improved |
| add deformable registration after rigid registration (ablation) | slice-to-volume registration · Heart MRI dataset | DICE, Hausdorff distance, CMD: DICE around 0.9; Hausdorff and CMD reduced around 66% | Improved |
| use Lazy Flipper instead of loopy belief propagation for the high-order model (ablation) | high-order approach · Heart and brain datasets | optimization time | Improved |
| use LBP instead of LF for large label spaces with smooth SAD energy (ablation) | decoupled and overparameterized approaches · Heart dataset | optimization time | Improved |
| change inference algorithm between LBP and LF (ablation) | all three approaches · Heart and brain datasets | final energy | No clear effect |
Closest papers by meaning
- Learning Deformable Image Registration From Optimization: Perspective, Modules, Bilevel Training and Beyond (TPAMI 2021 · similarity 0.88)
- NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration (CVPR 2022 · similarity 0.88)
- PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations (NeurIPS 2025 · similarity 0.87)
- An Unsupervised Learning Model for Deformable Medical Image Registration (CVPR 2018 · similarity 0.87)
- Higher-Order Graph Principles towards Non-Rigid Surface Registration (TPAMI 2016 · similarity 0.87)
- CARL: A Framework for Equivariant Image Registration (CVPR 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.
