AI Paper Atlas

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

CVPR 2026 · Video › Video segmentation and tracking · approach: Event-based video reconstruction

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 changedWhereMeasuredEffect
add aperture-modulation-triggered events and AENet/MENet fusion vs motion-only V2V-E2VIDAE2VID · EvAid (semi-real)MSE: 0.052 -> 0.037Improved
add aperture-modulation-triggered events vs motion-only V2V-E2VIDAE2VID · EvAid (semi-real)SSIM: 0.642 -> 0.707Improved
add aperture-modulation-triggered events vs motion-only V2V-E2VIDAE2VID · EvAid (semi-real)LPIPS: 0.409 -> 0.411No clear effect
add aperture-modulation-triggered events vs best motion-only baselinesAE2VID · HQFMSE: 0.041 -> 0.039Improved
add aperture-modulation-triggered events vs BDE2VIDAE2VID · HQFSSIM: 0.529 -> 0.585Improved
add aperture-modulation-triggered events vs BDE2VIDAE2VID · HQFLPIPS: 0.272 -> 0.352Hurt
periodically close and reopen the aperture to reset the observation windowAE2VID · design rationaleprediction error accumulationImproved
discard aperture-closing-triggered eventsAE2VID · design choiceinput qualityNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy