Research map / Time series / Causal and generative time series
Event Cameras, Contrast Maximization and Reward Functions: An Analysis
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 |
|---|---|---|---|
| Combine sparsity-rewarding and magnitude-rewarding criteria in rR1 (ablation) | Contrast maximization optical flow · Line segment sequence, E/N 1/0 | mean absolute magnitude error: 38.29 -> 10.31 | Helped |
| Add rSoE refinement to rR1 to form rR2 (ablation) | Contrast maximization optical flow · Line segment sequence, E/N 1/10 | mean absolute magnitude error: 55.33 -> 37.48 | Helped |
| Use the hybrid reward rather than rSoS (ablation) | Contrast maximization optical flow · Circle sequence, E/N 1/0 | mean absolute magnitude error: 0.49 -> 1.69 | Hurt |
| Use rR2 instead of rSoS (ablation) | Contrast maximization optical flow · Circle sequence, E/N 1/10 | mean absolute magnitude error: 43.41 -> 5.29 | Helped |
| Combine reward types in rR2 (ablation) | Contrast maximization optical flow · Office sequence, E/N 1/0 | mean absolute magnitude error: 5.58 -> 4.95 | Helped |
| Add rSoE refinement to rR1 to form rR2 (ablation) | Contrast maximization optical flow · Office sequence, E/N 1/0 | mean absolute magnitude error: 9.09 -> 4.95 | Helped |
| Use the hybrid reward instead of individual reward types (ablation) | Contrast maximization optical flow · Bicycle sequence, natural noise | mean absolute magnitude error: 22.12 -> 8.83 | Helped |
| Use magnitude-rewarding rather than sparsity-rewarding rewards (ablation) | Contrast maximization optical flow · Noisy event streams | mean absolute magnitude error | Mixed |
| Use sparsity-rewarding rather than magnitude-rewarding rewards (ablation) | Contrast maximization optical flow · Line segment sequence with aperture uncertainty | mean absolute magnitude error: 38.29 -> 11.36 | Helped |
| Use rSoE or rMoA in a noisy circle sequence (ablation) | Contrast maximization optical flow · Circle sequence, E/N 1/10 | mean absolute magnitude error: 72.14 -> 23.56; 73.45 -> 11.10 | Helped |
Closest papers by meaning
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.85)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.84)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.84)
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · similarity 0.84)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.84)
- Latency Correction for Event-guided Deblurring and Frame Interpolation (CVPR 2024 · similarity 0.84)
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.