Research map / Video / Video segmentation and tracking
A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
Ling Gao, Hang Su, Daniel Gehrig, Marco Cannici, Davide Scaramuzza, Laurent Kneip
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 |
|---|---|---|---|
| use eventail manifold model with 5-point solver instead of spatio-temporal plane clustering | event camera linear velocity estimation · VECtor (4 sequences) | success rate: 23%-70% -> 100% | Improved |
| use eventail solver on subset where CELC+opt succeeds | event camera linear velocity estimation · VECtor (4 sequences) | velocity direction error: e.g. 0.429 vs 0.451 (board-slow), 0.542 vs 0.483 (mountain-normal) | No clear effect |
| use eventail fitting instead of planes in high-dynamics simulation | event clustering · simulated high dynamics | clusters / velocity direction error: plane-based splits into 34 subsets; eventail error 0.01 rad | Improved |
| increase event noise level (ablation) | 5-point solver · synthetic single cluster | direction error | Hurt |
| ensure spatial distribution among the five sampled events (ablation) | 5-point solver sampling · synthetic single cluster | direction error | Improved |
| violate constant-velocity assumption (smaller arc radius, larger acceleration) (ablation) | 5-point solver in RANSAC · EGG simulation, 10 eventails | direction error | Hurt |
| run sequential RANSAC on all events when cilantro clustering fails (ablation) | eventail pipeline · VECtor | success rate: 100% success | Improved |
Closest papers by meaning
- An N-Point Linear Solver for Line and Motion Estimation with Event Cameras (CVPR 2024 · similarity 0.93)
- Motion and Structure from Event-based Normal Flow (ECCV 2024 · similarity 0.90)
- The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data (ICCV 2021 · similarity 0.89)
- A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks (ICCV 2025 · similarity 0.89)
- Full-DoF Egomotion Estimation for Event Cameras Using Geometric Solvers (CVPR 2025 · similarity 0.88)
- 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.
