AI Paper Atlas

Research map / Video / Video segmentation and tracking

DVS-Voltmeter: Stochastic Process-Based Event Simulator for Dynamic Vision Sensors

Songnan Lin, Ye Ma, Zhenhua Guo, Bihan Wen

ECCV 2022 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 53 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
train on DVS-Voltmeter events instead of Vid2E eventssegmentation network · Ev-Seg (before fine-tuning)MIoU: 46.67 -> 50.60Improved
train on DVS-Voltmeter events instead of V2E eventssegmentation network · Ev-Seg (before fine-tuning)MIoU: 42.25 -> 50.60Improved
train on DVS-Voltmeter events instead of Vid2E eventssegmentation network · Ev-Seg (before fine-tuning)accuracy: 84.95 -> 87.88Improved
fine-tune on 20 real samples after pretraining on DVS-Voltmeter eventssegmentation network · Ev-SegMIoU: 50.60 -> 51.20Improved
pretrain on simulated events before fine-tuning on 20 real samples instead of training on 20 real samples onlysegmentation network · Ev-SegMIoU: 24.39 -> 51.20Improved
use simulated events from DVS-Voltmeter instead of all real training samplessegmentation network · Ev-SegMIoU: 54.81 -> 50.60Hurt
train on DVS-Voltmeter events instead of Vid2E eventsreconstruction network · Event Camera Dataset (mean)MSE: 0.056 -> 0.034Improved
train on DVS-Voltmeter events instead of V2E eventsreconstruction network · Event Camera Dataset (mean)MSE: 0.122 -> 0.034Improved
train on DVS-Voltmeter events instead of Vid2E eventsreconstruction network · Event Camera Dataset (mean)SSIM: 0.505 -> 0.550Improved
train on DVS-Voltmeter events instead of Vid2E eventsreconstruction network · Event Camera Dataset (mean)LPIPS: 0.413 -> 0.397Improved
train on DVS-Voltmeter events instead of Vid2E eventsreconstruction network · Event Camera Dataset (dynamic 6dof)LPIPS: 0.367 -> 0.405Hurt

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