Research map / Image generation / Image restoration
DFMN: A Dual-feet Matching Network with Hybrid Transformer-based Feature Extractor for Unsupervised Deformable Medical Image Registration
Liwen Li, Xinrui Guo, Wentao Guo, Shunqi Yang, Fumin Guo
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 |
|---|---|---|---|
| use DFEnc multi-step patch conv encoder instead of standard patch-embedding transformer (ablation) | DFMN · ACDC | mean DSC (%): 80.2 -> 81.8 | Improved |
| use DFEnc instead of conv encoder (ablation) | DFMN · ACDC | mean DSC (%): 78.6 -> 81.8 | Improved |
| add SSHExt hybrid extractor (ablation) | DFMN · ACDC | mean DSC (%): 80.9 -> 81.8 | Improved |
| add dense connections (ablation) | DFMN · ACDC | mean DSC (%): 80.9 -> 81.8 | Improved |
| add FFDec instead of conv decoder (ablation) | DFMN · ACDC | mean DSC (%): 75.9 -> 81.8 | Improved |
| coarse-to-fine multi-stage deformation instead of single pass (ablation) | DFMN · ACDC | mean DSC (%): 79.8 -> 81.8 | Improved |
| add Swin blocks in FFDec (ablation) | DFMN · ACDC | mean DSC (%): 79.1 -> 81.8 | Improved |
| use FFLayer instead of convolutions (ablation) | DFMN · ACDC | mean DSC (%): 76.1 -> 81.8 | Improved |
| DFMN vs AutoFuse-Trans | DFMN · ACDC (main comparison) | mean DSC (%): 80.82 -> 81.96 | Improved |
| DFMN vs AutoFuse-Trans | DFMN · OASIS | mean DSC (%): 80.23 -> 82.00 | Improved |
| DFMN vs AutoFuse-Trans | DFMN · Abdomen CT | mean DSC (%): 57.28 -> 61.75 | Improved |
| DFMN vs AutoFuse-Trans on folding rate | DFMN · ACDC / Abdomen CT | negative Jacobian (%): 0.18 -> 0.26 (ACDC); 3.60 -> 3.89 (Abdomen CT) | Mixed |
Closest papers by meaning
- Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration (CVPR 2024 · similarity 0.87)
- H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration (CVPR 2024 · similarity 0.86)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.85)
- A Plug-and-Play Image Registration Network (ICLR 2024 · similarity 0.85)
- SACB-Net: Spatial-awareness Convolutions for Medical Image Registration (CVPR 2025 · similarity 0.85)
- 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.
