AI Paper Atlas

Research map / Video / Video segmentation and tracking

Globally-Optimal Event Camera Motion Estimation

Xin Peng, Yifu Wang, Ling Gao, Laurent Kneip

ECCV 2020 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 28 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 SoSAaS contrast instead of SoS (ablation)GOCMF · Foam dataset, curve motionRMS error of w (deg/s): 3.0091 -> 0.5546Improved
use SoSAaS contrast instead of SoS (ablation)GOCMF · Foam dataset, circle motionRMS error of w (deg/s): 1.0884 -> 0.5294Improved
use SoSAaS contrast instead of SoS (ablation)GOCMF · Foam dataset, line motionRMS error of w (deg/s): 0.5127 -> 0.5175No clear effect
use SoSA contrast instead of SoS (ablation)GOCMF · Foam dataset, curve motionRMS error of w (deg/s): 3.0091 -> 9.2904Hurt
use SoE contrast instead of SoS (ablation)GOCMF · Foam dataset, line motionRMS error of w (deg/s): 0.5127 -> 2.4089Hurt
use SoEaS contrast instead of SoS (ablation)GOCMF · Foam dataset, curve motionRMS error of w (deg/s): 3.0091 -> 3.6282Hurt
replace gradient ascent (best initialisation) with globally optimal BnB (ablation)SoS contrast maximisation · Foam dataset, curve motionRMS error of w (deg/s): 11.5023 -> 3.0091Improved
replace gradient ascent (best initialisation) with globally optimal BnB (ablation)SoS contrast maximisation · Foam dataset, curve motionRMS error of v (m/s): 0.0379 -> 0.0208Improved
use event-based SoSAaS instead of frame-based GOVOAGV motion estimation · Foam dataset, curve motionRMS error of w (deg/s): 9.8652 -> 0.5546Improved
use event-based SoSAaS instead of frame-based IFMIAGV motion estimation · Foam dataset, line motionRMS error of w (deg/s): 145.3741 -> 0.5175Improved
add salt-and-pepper noise up to N/E 0.4 (ablation)BnB with SoS · Simulated line segmentsparameter errorNo clear effect
use BnB instead of exhaustive searchSoS contrast maximisation · Simulated line segments, noise-freestd of w error (deg/s): 1.0645 -> 1.305No 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