Research map / Video / Video segmentation and tracking
Physical-Based Event Camera Simulator
Haiqian Han, Jiacheng Lyu, Jianing Li, Henglu Wei, Cheng Li, Yajing Wei, SHU CHEN, Xiangyang Ji
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 Monte Carlo/numerical integration sampling number N from 6 to 31 (ablation) | PECS multispectral rendering · Rotate 360 High | Chamfer distance: 8.588 -> 2.008 | Improved |
| increase sampling number N from 6 to 31 (ablation) | PECS multispectral rendering · Rotate 360 High | Gaussian distance: 1.583 -> 0.964 | Improved |
| increase N raises computation time (ablation) | PECS · Rotate 360 High | computation cost | Hurt |
| vary hyperparameter C from 10 to 160 (ablation) | PECS · Rotate 360 High | Chamfer distance: best 2.008 at C=100 | Mixed |
| use PECS-simulated events to train E2VID instead of V2E events | E2VID · HS-ERGB real sequences | PSNR: 8.997 -> 9.678 | Improved |
| use PECS events instead of V2E events for LPIPS | E2VID · HS-ERGB real sequences | LPIPS: 0.464 -> 0.447 | Improved |
| use PECS vs ICNS on Gaussian distance in low-light translating scene | PECS · Trans 1mps Low | Gaussian distance: 1.663 -> 1.710 | Hurt |
| render physical lens and multispectral photocurrent versus video-to-event simulators | PECS · six recorded sequences | Chamfer distance: 6.735 -> 3.631 vs ICNS | Improved |
Closest papers by meaning
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.86)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.85)
- Hybrid Event–Frame Sensors: Modeling, Calibration, and Simulation (ECCV 2026 · similarity 0.85)
- GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation (NeurIPS 2025 · similarity 0.84)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.83)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.83)
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.
