Research map / Video / Video segmentation and tracking
Globally-Optimal Event Camera Motion Estimation
Xin Peng, Yifu Wang, Ling Gao, 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 SoSAaS contrast instead of SoS (ablation) | GOCMF · Foam dataset, curve motion | RMS error of w (deg/s): 3.0091 -> 0.5546 | Improved |
| use SoSAaS contrast instead of SoS (ablation) | GOCMF · Foam dataset, circle motion | RMS error of w (deg/s): 1.0884 -> 0.5294 | Improved |
| use SoSAaS contrast instead of SoS (ablation) | GOCMF · Foam dataset, line motion | RMS error of w (deg/s): 0.5127 -> 0.5175 | No clear effect |
| use SoSA contrast instead of SoS (ablation) | GOCMF · Foam dataset, curve motion | RMS error of w (deg/s): 3.0091 -> 9.2904 | Hurt |
| use SoE contrast instead of SoS (ablation) | GOCMF · Foam dataset, line motion | RMS error of w (deg/s): 0.5127 -> 2.4089 | Hurt |
| use SoEaS contrast instead of SoS (ablation) | GOCMF · Foam dataset, curve motion | RMS error of w (deg/s): 3.0091 -> 3.6282 | Hurt |
| replace gradient ascent (best initialisation) with globally optimal BnB (ablation) | SoS contrast maximisation · Foam dataset, curve motion | RMS error of w (deg/s): 11.5023 -> 3.0091 | Improved |
| replace gradient ascent (best initialisation) with globally optimal BnB (ablation) | SoS contrast maximisation · Foam dataset, curve motion | RMS error of v (m/s): 0.0379 -> 0.0208 | Improved |
| use event-based SoSAaS instead of frame-based GOVO | AGV motion estimation · Foam dataset, curve motion | RMS error of w (deg/s): 9.8652 -> 0.5546 | Improved |
| use event-based SoSAaS instead of frame-based IFMI | AGV motion estimation · Foam dataset, line motion | RMS error of w (deg/s): 145.3741 -> 0.5175 | Improved |
| add salt-and-pepper noise up to N/E 0.4 (ablation) | BnB with SoS · Simulated line segments | parameter error | No clear effect |
| use BnB instead of exhaustive search | SoS contrast maximisation · Simulated line segments, noise-free | std of w error (deg/s): 1.0645 -> 1.305 | No clear effect |
Closest papers by meaning
- Globally-Optimal Contrast Maximisation for Event Cameras (TPAMI 2021 · similarity 0.94)
- Simultaneous Optical Flow and Intensity Estimation From an Event Camera (CVPR 2016 · similarity 0.90)
- Globally Optimal Contrast Maximisation for Event-Based Motion Estimation (CVPR 2020 · similarity 0.89)
- A Unifying Contrast Maximization Framework for Event Cameras, With Applications to Motion, Depth, and Optical Flow Estimation (CVPR 2018 · similarity 0.89)
- Event based Multi-Velocity-Scale Imaging (NeurIPS 2026 · similarity 0.88)
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (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.
