Research map / Probabilistic and scientific modeling / Molecules and proteins
Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific Data
Osamu Hirose, Emanuele Rodola
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 DET instead of geometry-only BCPD | DET · MERFISH 90-case | Jaccard overlap: 0.612 -> 0.881 | Improved |
| use DET instead of geometry-only BCPD | DET · MERFISH 90-case | smoothed PCC: 0.366 -> 0.736 | Improved |
| use DET instead of PASTE2-DS-1NN | DET · MERFISH 90-case | topology score: 0.394 -> 0.928 | Improved |
| use PASTE2-DS-1NN instead of DET for label transfer | PASTE2-DS-1NN · MERFISH 90-case | label-transfer ARI: 0.185 -> 0.194 | Improved |
| use DET instead of STalign | DET · MERFISH 90-case | runtime (s): 142.00 -> 8.58 | Improved |
| use DET instead of BCPD | DET · MERFISH 90-case | runtime (s): 2.98 -> 8.58 | Hurt |
| add nonrigid L2 refinement after L1 similarity | DET · MOSTA E14.5-to-E15.5 | occupancy Jaccard: 0.901 -> 0.971 | Improved |
| add nonrigid L2 refinement after L1 similarity | DET · MOSTA E14.5-to-E15.5 | topology: 0.902 -> 0.883 | Hurt |
| add VGIS instead of uniform downsampling in L2 (ablation) | DET · MOSTA E14.5-to-E15.5 | smoothed PCC: 0.124 -> 0.126 | No clear effect |
| add VGIS instead of uniform downsampling in L2 (ablation) | DET · MOSTA E14.5-to-E15.5 | occupancy Jaccard: 0.971 -> 0.964 | Hurt |
| add dimensionality balancing zeta = eta (D/D') (ablation) | DET · MERFISH 27-case subset | success rate: unbalanced diagnostic failed in all 27 cases | Improved |
| add functional annealing over fixed functional weight (ablation) | DET · MERFISH 27-case subset | registration quality | Improved |
Closest papers by meaning
- Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration (ECCV 2026 · similarity 0.85)
- Fourier-Net: Fast Image Registration with Band-Limited Deformation (AAAI 2023 · similarity 0.85)
- Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance (NeurIPS 2026 · similarity 0.84)
- Inductive Domain Transfer In Misspecified Simulation-Based Inference (NeurIPS 2025 · similarity 0.84)
- Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging (ICLR 2025 · similarity 0.83)
- Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images (ICLR 2025 · 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.
