Research map / Video / Video segmentation and tracking
AE2VID: Event-based Video Reconstruction via Aperture Modulation
Chenxu Bai, Boyu Li, Peiqi Duan, Xinyu Zhou, Hanyue Lou, Boxin Shi
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 aperture-modulation-triggered events and AENet/MENet fusion vs motion-only V2V-E2VID | AE2VID · EvAid (semi-real) | MSE: 0.052 -> 0.037 | Improved |
| add aperture-modulation-triggered events vs motion-only V2V-E2VID | AE2VID · EvAid (semi-real) | SSIM: 0.642 -> 0.707 | Improved |
| add aperture-modulation-triggered events vs motion-only V2V-E2VID | AE2VID · EvAid (semi-real) | LPIPS: 0.409 -> 0.411 | No clear effect |
| add aperture-modulation-triggered events vs best motion-only baselines | AE2VID · HQF | MSE: 0.041 -> 0.039 | Improved |
| add aperture-modulation-triggered events vs BDE2VID | AE2VID · HQF | SSIM: 0.529 -> 0.585 | Improved |
| add aperture-modulation-triggered events vs BDE2VID | AE2VID · HQF | LPIPS: 0.272 -> 0.352 | Hurt |
| periodically close and reopen the aperture to reset the observation window | AE2VID · design rationale | prediction error accumulation | Improved |
| discard aperture-closing-triggered events | AE2VID · design choice | input quality | No clear effect |
Closest papers by meaning
- High Speed and High Dynamic Range Video with an Event Camera (TPAMI 2019 · similarity 0.90)
- LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction (NeurIPS 2024 · similarity 0.89)
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.88)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (AAAI 2024 · similarity 0.88)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.87)
- Unified Reconstruction of Static and Dynamic Scenes from Events (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.
