Research map / Image generation / Image restoration
Deep Lucas-Kanade Homography for Multimodal Image Alignment
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Refine the DHN homography with DLKFM and Lucas-Kanade | DHN · Google Earth cross-season test | <3 pixel success rate: 0% -> 60% | Helped |
| Refine the MHN homography with DLKFM and Lucas-Kanade | MHN · Google Earth cross-season test | <3 pixel success rate: 1% -> 66% | Helped |
| Refine the DHN homography with DLKFM and Lucas-Kanade | DHN · GoogleMap test | <3 pixel success rate: 0% -> 52% | Helped |
| Refine the MHN homography with DLKFM and Lucas-Kanade | MHN · GoogleMap test | <3 pixel success rate: 0% -> 60% | Helped |
| Refine the DHN homography with DLKFM and Lucas-Kanade | DHN · MSCOCO test | <10 pixel success rate: 97% -> 97% | No clear effect |
| Replace regular one-filter convolution with the DLKFM feature constructor (ablation) | DHN-initialized alignment · Google Earth cross-season test | <3 pixel success rate: 47% -> 60% | Helped |
| Replace regular one-filter convolution with the DLKFM feature constructor (ablation) | MHN-initialized alignment · Google Earth cross-season test | <10 pixel success rate: 83% -> 91% | Helped |
Closest papers by meaning
- FastJAM: a Fast Joint Alignment Model for Images (NeurIPS 2025 · similarity 0.86)
- Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization (NeurIPS 2024 · similarity 0.86)
- Adapting Dense Matching for Homography Estimation with Grid-based Acceleration (CVPR 2025 · similarity 0.84)
- With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You (NeurIPS 2025 · similarity 0.84)
- MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation (CVPR 2024 · similarity 0.83)
- Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning (NeurIPS 2026 · 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.