Research map / Image generation / Autoregressive and latent generation
$\mathcal {X}$-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing
Xinzhe Luo, Xiahai Zhuang
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 ground-truth appearance model instead of estimated one (X-Reg-GT vs X-Reg-UN) (ablation) | X-Reg · BrainWeb (nonrigid, 3 modalities) | gWI (mm): 0.476 -> 0.485 | No clear effect |
| use anatomical common-space representation instead of PCA grey-valued template (CTE) | X-Reg · BrainWeb (nonrigid, 3 modalities) | gWI (mm): 0.545 -> 0.476 | Improved |
| use pairwise-MI accumulation (APE) instead of X-metric | X-Reg-UN · BrainWeb (nonrigid, 3 modalities) | gWI (mm): 0.476 -> 0.411 | Mixed |
| use X-CoReg instead of GMM | GMM · RIRE (rigid, 8 images) | gRE (mm): 15.84 -> 5.52 | Improved |
| use X-CoReg instead of CTE | CTE · RIRE (rigid, 8 images) | gRE (mm): 13.46 -> 5.52 | Improved |
| use X-CoReg instead of APE | APE · RIRE (rigid, 8 images) | gRE (mm): 5.36 -> 5.52 | No clear effect |
| use X-CoReg instead of APE | APE · RIRE (rigid, 8 images) | time ratio: 2.02 -> 1.00 | Improved |
| increase number of common anatomical labels K up to about 10 (ablation) | X-CoReg · RIRE (rigid, 8 images) | gRE (mm) | Improved |
Closest papers by meaning
- Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration (TPAMI 2025 · similarity 0.88)
- Metric Learning for Image Registration (CVPR 2019 · similarity 0.86)
- An Unsupervised Learning Model for Deformable Medical Image Registration (CVPR 2018 · similarity 0.86)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.86)
- Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration (CVPR 2024 · similarity 0.85)
- Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance (NeurIPS 2026 · 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.
