AI Paper Atlas

Research map / Video / Video segmentation and tracking

Event-based Visual Vibrometry

Xinyu Zhou, Peiqi Duan, Yeliduosi Xiaokaiti, Chao Xu, Boxin Shi

ICCV 2025 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 4 citations (OpenAlex)

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 the motion refinement network to coarse optimization (ablation)EVibNet · synthetic dataEPE: 0.3632 -> 0.0834Improved
add the motion refinement network to coarse optimization (ablation)EVibNet · synthetic data% Out: 51.45 -> 21.29Improved
add coarse motion from optimization as network input (ablation)EVibNet · synthetic dataEPE: 0.0969 -> 0.0834Improved
add the motion accumulation module (ablation)EVibNet · synthetic dataEPE: 0.1299 -> 0.0834Improved
add the reference frame as input (ablation)EVibNet · synthetic dataEPE: 0.1734 -> 0.0834Improved
add the reference frame as input (ablation)EVibNet · synthetic data% Out: 42.25 -> 21.29Improved
use event + single frame method instead of event-only EV-FlowNetEVibNet · synthetic dataEPE: 0.1805 -> 0.0834Improved
use event method instead of 960Hz frame RGBPhaseEVibNet · synthetic dataEPE: 0.2833 -> 0.0834Improved
use refinement network instead of cascading EMM with RAFTEVibNet · synthetic dataEPE: 0.2190 -> 0.0834Improved
use event-based estimate instead of 1000 fps videoEvent vibrometry · Young's modulus, aluminum 35 cm, low lightpercent error: 10.01 -> 2.90Improved
use event-based estimate instead of 1000 fps videoEvent vibrometry · Young's modulus, steel 35 cm, medium lightpercent error: -10.72 -> -6.77Improved
use existing event optical flow (EV-FlowNet, MCM) for rod vibrationEV-FlowNet and MCM · rod vibrationresonant frequency recoveryHurt

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