Research map / Video / Video segmentation and tracking
EKLT: Asynchronous Photometric Feature Tracking Using Events and Frames
Daniel Gehrig, Henri Rebecq, Guillermo Gallego, Davide Scaramuzza
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 |
|---|---|---|---|
| increase patch size from 5x5 to 25x25 (ablation) | EKLT · sim april tags | pixel error: 3.04 -> 0.20 | Improved |
| increase patch size from 5x5 to 25x25 (ablation) | EKLT · poster 6dof | pixel error: 11.59 -> 0.67 | Improved |
| increase patch size from 5x5 to 25x25 (ablation) | EKLT · boxes 6dof | pixel error: 7.24 -> 0.89 | Improved |
| increase patch size from 25x25 to 35x35 (ablation) | EKLT · sim april tags | pixel error: 0.20 -> 0.16 | Improved |
| increase patch size from 25x25 to 35x35 (ablation) | EKLT · shapes 6dof | pixel error: 0.64 -> 0.62 | No clear effect |
| increase patch size from 25x25 to 35x35 (ablation) | EKLT · checkerboard | pixel error: 0.78 -> 0.75 | No clear effect |
| increase patch size from 5x5 to 11x11 (ablation) | EKLT · sim april tags | feature age: 0.23 -> 0.98 | Improved |
| increase patch size from 5x5 to 25x25 (ablation) | EKLT · sim rocks | feature age: 0.05 -> 1.00 | Improved |
| increase patch size from 25x25 to 35x35 (ablation) | EKLT · sim april tags | feature age: 1.52 -> 1.20 | Hurt |
| increase patch size from 15x15 to 25x25 (ablation) | EKLT · sim april tags | feature age: 2.33 -> 1.52 | Hurt |
| increase patch size from 5x5 to 25x25 (ablation) | EKLT · checkerboard | feature age: 2.68 -> 8.24 | Improved |
| integrate too few or too many events per patch (Ne=10 or 1000 vs intermediate) (ablation) | EKLT · patch objective shape | registration reliability | Hurt |
Closest papers by meaning
- Asynchronous, Photometric Feature Tracking using Events and Frames (ECCV 2018 · similarity 0.97)
- Data-Driven Feature Tracking for Event Cameras With and Without Frames (TPAMI 2025 · similarity 0.91)
- Data-Driven Feature Tracking for Event Cameras (CVPR 2023 · similarity 0.89)
- Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds (ICCV 2021 · similarity 0.89)
- ETAP: Event-based Tracking of Any Point (CVPR 2025 · similarity 0.87)
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · similarity 0.87)
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.
