Research map / Video / Video segmentation and tracking
Data-Driven Feature Tracking for Event Cameras With and Without Frames
Nico Messikommer, Carter Fang, Mathias Gehrig, Giovanni Cioffi, 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 |
|---|---|---|---|
| add correlation map (ablation) | reference model · EDS | Expected feature age: 0.341 -> 0.383 | Improved |
| add correlation map (ablation) | reference model · EC | Expected feature age: 0.684 -> 0.787 | Improved |
| add recurrence in feature encoder (ablation) | reference model · EDS | Expected feature age: 0.301 -> 0.383 | Improved |
| add recurrence in feature encoder (ablation) | reference model · EC | Expected feature age: 0.606 -> 0.787 | Improved |
| add augmentation during synthetic training (ablation) | reference model · EDS | Expected feature age: 0.178 -> 0.383 | Improved |
| add augmentation during synthetic training (ablation) | reference model · EC | Expected feature age: 0.599 -> 0.787 | Improved |
| add frame attention module (ablation) | reference model · EDS | Expected feature age: 0.383 -> 0.451 | Improved |
| add frame attention module (ablation) | reference model · EC | Expected feature age: 0.787 -> 0.787 | No clear effect |
| add pose supervision fine-tuning (ablation) | Ref + Frame Attention · EDS | Expected feature age: 0.451 -> 0.471 | Improved |
| add pose supervision fine-tuning (ablation) | Ref + Frame Attention · EC | Expected feature age: 0.787 -> 0.818 | Improved |
| add state variables in frame attention (ablation) | Ref + Frame Attention · EDS | Expected feature age: 0.385 -> 0.451 | Improved |
| replace gating network with LSTM (ablation) | Ref + Frame Attention · EDS | Expected feature age: 0.451 -> 0.423 | Hurt |
Closest papers by meaning
- Data-Driven Feature Tracking for Event Cameras (CVPR 2023 · similarity 0.95)
- Asynchronous, Photometric Feature Tracking using Events and Frames (ECCV 2018 · similarity 0.92)
- EKLT: Asynchronous Photometric Feature Tracking Using Events and Frames (IJCV 2019 · similarity 0.91)
- ETAP: Event-based Tracking of Any Point (CVPR 2025 · similarity 0.89)
- 3D Feature Tracking via Event Camera (CVPR 2024 · similarity 0.89)
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline (CVPR 2024 · 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.
