Research map / Image generation / GANs
Generative Adversarial Registration for Improved Conditional Deformable Templates
Neel Dey, Mengwei Ren, Adrian V. Dalca, Guido Gerig
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 discriminator (adversarial loss) to VXM (ablation) | VXM · Predict-HD (conditional) | moving-average deformation norm: 221.68 -> 208.61 | Improved |
| add FiLM-conditioned architecture to adversarial model (ablation) | Ablation/VXM+Adv · dHCP (conditional) | moving-average deformation norm: 215.90 -> 167.62 | Improved |
| add discriminator to our architecture (ablation) | Ablation/noAdv · Predict-HD (conditional) | moving-average deformation norm: 199.39 -> 175.01 | Improved |
| add discriminator to our architecture (ablation) | Ablation/noAdv · dHCP (conditional) | entropy focus criterion: 0.903 ± 0.007 -> 0.885 ± 0.009 | Improved |
| add discriminator to our architecture (ablation) | Ablation/noAdv · Predict-HD (unconditional) | moving-average deformation norm: 271.00 -> 224.68 | Improved |
| add discriminator to our architecture (ablation) | Ablation/noAdv · dHCP (unconditional) | moving-average deformation norm: 285.55 -> 250.27 | Improved |
| add discriminator to VXM (ablation) | VXM · Predict-HD (unconditional) | entropy focus criterion: 0.872 -> 0.868 | Improved |
| add discriminator to VXM (ablation) | VXM · dHCP (unconditional) | moving-average deformation norm: 251.48 -> 261.36 | Hurt |
| use our architecture with discriminator instead of VXM | VXM · Predict-HD (conditional) | moving-average deformation norm: 221.68 -> 175.01 | Improved |
| use our architecture with discriminator instead of VXM | VXM · dHCP (conditional) | average deformation norm: 3844 ± 230 -> 3609 ± 226 | Improved |
| use our method instead of VXM | VXM · Predict-HD and dHCP (conditional) | Dice: 0.75 ± 0.02 -> 0.75 ± 0.02 | No clear effect |
| use our method instead of ANTs SyGN | ANTs SyGN · dHCP (unconditional) | average deformation norm: 2687 ± 345 -> 3815 ± 232 | Hurt |
Closest papers by meaning
- Learning Conditional Deformable Templates with Convolutional Networks (NeurIPS 2019 · similarity 0.91)
- SymReg-GAN: Symmetric Image Registration with Generative Adversarial Networks (TPAMI 2021 · similarity 0.87)
- Deep Learning in Medical Image Registration: Magic or Mirage? (NeurIPS 2024 · similarity 0.84)
- A Plug-and-Play Image Registration Network (ICLR 2024 · similarity 0.84)
- Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance (NeurIPS 2026 · similarity 0.84)
- Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration (CVPR 2024 · similarity 0.83)
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.
