Research map / Vision-language and multimodal / Cross-modal learning
RBE-Flow:Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration
Mengzhu Ding, Xin Song, Xiaoke Ding, Hongwei Ding, Xuecong Liu
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 GFI global flow initialization (ablation) | A+L1 · WHU-OPT-SAR | AEPE (px): 5.52 -> 1.10 | Improved |
| add GFI global flow initialization (ablation) | A+L1 · OSdataset | CMR @1px (%): 22.9 -> 61.8 | Improved |
| replace L1 loss with geometry-aware rectified NLL loss (ablation) | A+L1+GFI · WHU-OPT-SAR | CMR @1px (%): 47.3 -> 82.9 | Improved |
| add RMO block (ablation) | A+GFI+loss · RoadScene | CMR @0.3px (%): 12.6 -> 26.9 | Improved |
| add RMO block (ablation) | A+GFI+loss · WHU-OPT-SAR | AEPE (px): 0.76 -> 0.61 | Improved |
| add UAPU block (ablation) | A+GFI+loss+RMO · OSdataset | CMR @0.3px (%): 3.1 -> 11.6 | Improved |
| add UAPU block (ablation) | A+GFI+loss+RMO · WHU-OPT-SAR | CMR @0.3px (%): 11.9 -> 24.0 | Improved |
| add UAPU block (ablation) | A+GFI+loss+RMO · OSdataset | AEPE (px): 0.84 -> 0.77 | Improved |
| add GFI global flow initialization (ablation) | A+L1 · RoadScene | CMR @0.7px (%): 76.0 -> 67.0 | Hurt |
Closest papers by meaning
- Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation (NeurIPS 2026 · similarity 0.86)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.86)
- Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework (AAAI 2025 · similarity 0.84)
- Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance (NeurIPS 2026 · similarity 0.84)
- Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching (NeurIPS 2024 · similarity 0.84)
- Variational Rectified Flow Matching (ICML 2025 · 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.
