AI Paper Atlas

Research map / Video / Video segmentation and tracking

Selfie Video Stabilization

Jiyang Yu, Ravi Ramamoorthi

ECCV 2018 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 48 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
stabilize with the proposed 3D-face plus optical-flow method instead of Liu et al. and Grundmann et al.selfie video stabilization · Selfie video dataset (33 clips)smoothness measure (lower is better)Improved
track background with optical flow instead of feature pointsvideo stabilization · Selfie clips with few background featuressmoothness measureImproved
add foreground head-trajectory regularization term (ablation)selfie video stabilization · Selfie video dataset (33 clips)field of view / over-stabilizationImproved
drop the head term Eh for general videos (ablation)selfie video stabilization · General videos (6 clips)smoothness measureNo clear effect
vary head regularization weight lambda_a (ablation)selfie video stabilization · Selfie video dataset (33 clips)foreground vs background stabilizationMixed
vary grid rigidity weight lambda_b (ablation)selfie video stabilization · Selfie video dataset (33 clips)stabilization 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