Research map / Image generation / Image restoration
Learning Deformable Image Registration From Optimization: Perspective, Modules, Bilevel Training and Beyond
Risheng Liu, Zi Li, Xin Fan, Chenying Zhao, Hao Huang, Zhongxuan Luo
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 feature extraction network (FEN) (ablation) | 3-scale model · OASIS brain MR | Dice score: 0.764 -> 0.777 | Improved |
| add feature extraction network (FEN) (ablation) | 2-scale model · HCP brain MR | Dice score: 0.698 -> 0.759 | Improved |
| add regularization network (RN) (ablation) | 3-scale model · OASIS brain MR | Dice score: 0.771 -> 0.777 | Improved |
| add regularization network (RN) (ablation) | 2-scale model · ABIDE brain MR | Dice score: 0.746 -> 0.745 | No clear effect |
| go from 3-scale to 4-scale (ablation) | model with RN · OASIS brain MR | Dice score: 0.777 -> 0.774 | No clear effect |
| use six-layer matching network instead of one layer (ablation) | Matching network · OASIS brain MR | Dice score: 0.751 -> 0.781 | Improved |
| use six-layer regularization network instead of one layer (ablation) | Regularization network · OASIS brain MR | Dice score: 0.771 -> 0.774 | Improved |
| add bilevel self-tuned training (ablation) | Registration network · OASIS brain MR | Dice score: 0.777 -> 0.776 | No clear effect |
| add bilevel self-tuned training (ablation) | Registration network · OASIS brain MR | NCC: 0.245 -> 0.257 | Improved |
| add bilevel self-tuned training (ablation) | Registration network · SLIVER liver CT | Dice score: 0.883 -> 0.910 | Improved |
| add bilevel self-tuned training (ablation) | Registration network · LSPIG liver CT | Dice score: 0.822 -> 0.855 | Improved |
| add affine network (ablation) | Registration network · SLIVER liver CT | Dice score: 0.858 -> 0.910 | Improved |
Closest papers by meaning
- NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration (CVPR 2022 · similarity 0.92)
- Deep Learning in Medical Image Registration: Magic or Mirage? (NeurIPS 2024 · similarity 0.89)
- A Plug-and-Play Image Registration Network (ICLR 2024 · similarity 0.88)
- H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration (CVPR 2024 · similarity 0.88)
- Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration (CVPR 2024 · similarity 0.88)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.88)
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.
