AI Paper Atlas

Research map / Video / Video segmentation and tracking

An Asynchronous Kalman Filter for Hybrid Event Cameras

Ziwei Wang, Yonhon Ng, Cedric Scheerlinck, Robert Mahony

ICCV 2021 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 50 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
use per-pixel Kalman gain from event/frame uncertainty model and frame augmentation instead of a constant gain complementary filterAKF vs CF · HDR datasetMSE (x10^-2): 6.22 -> 1.71Improved
use per-pixel Kalman gain from uncertainty model instead of constant gain complementary filterAKF vs CF · AHDR datasetMSE (x10^-2): 5.28 -> 4.18Improved
add frame information to events (AKF vs events-only E2VID)AKF · HDR datasetSSIM: 0.616 -> 0.89Improved
add frame information to events (AKF vs events-only ECNN)AKF · AHDR datasetSSIM: 0.04 -> 0.75Improved
use frame information with a constant-gain filter (CF) instead of events-only networksCF vs E2VID/ECNN · HDR datasetQ-score: 4.32 -> 3.01Hurt
use AKF versus the compared methods on averageAKF · HDR/AHDR datasetsMSE; SSIM and Q-score: 48% MSE reduction; 11% improvement in SSIM and Q-score on averageImproved

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