Research map / Image generation / Image restoration
Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing
Armand Zampieri, Guillaume Charpiat, Nicolas Girard, Yuliya Tarabalka
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 |
|---|---|---|---|
| restrict alignment to a single scale (r=2) instead of full r=20 range (ablation) | two-stream fully-convolutional network · Single-scale task s=0 | bin accuracy (%): 6% -> 90% | Improved |
| average over 8 symmetrised/rotated inputs (sym-inv) (ablation) | multiscale chain · Forez keypoint matching | percentage of correct keypoints | Improved |
| share one s=2 block across scales (scale-inv) instead of scale-specific blocks (ablation) | multiscale chain · Kitsap and Forez keypoint matching | percentage of correct keypoints | Mixed |
Closest papers by meaning
- Sparse-to-dense Multimodal Image Registration via Multi-Task Learning (ICML 2024 · similarity 0.87)
- Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement (CVPR 2026 · similarity 0.87)
- Recurrent Registration Neural Networks for Deformable Image Registration (NeurIPS 2019 · similarity 0.85)
- Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation (CVPR 2020 · similarity 0.85)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.84)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (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.
