AI Paper Atlas

Research map / Video / Video generation

Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization

Muhammad Kashif Ali, Eun Woo Im, D Kim, Tae Hyun Kim, Vivek Gupta, Haonan Luo, Tianrui Li

TPAMI 2026 · Video › Video generation · approach: Trajectory-guided motion control · 3 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 targeted (jerk-localized) adaptation instead of random-sequence adaptation (ablation)DIFRINT · NUSstability score: 0.8528 -> 0.8620Improved
use targeted rather than vanilla adaptation (ablation)DIFRINT · NUSdistortion: 0.9596 -> 0.9354Hurt
raise number of adapted peak sequences p from 10 to 100 in targeted adaptation (ablation)DIFRINT + TargetedAdapt · NUSstability score: 0.8620 -> 0.8680Improved
raise p from 10 to 100 in targeted adaptation (ablation)DIFRINT + TargetedAdapt · NUSdistortion: 0.9354 -> 0.9542Improved
add test-time meta-adaptation (1 pass, 100 sequences) to DIFRINTDIFRINT · NUSstability score: 0.7904 -> 0.8428Improved
add one adaptation pass over all sequences to DIFRINTDIFRINT · NUSstability score: 0.7904 -> 0.8786Improved
add vanilla adaptation over all sequences to DMBVSDMBVS · NUSstability score: 0.7372 -> 0.7760Improved
add targeted adaptation and recurrent formulation to DMBVSDMBVS · DOFVSstability score: 0.7577 -> 0.8253Improved
add targeted adaptation to DIFRINTDIFRINT · DOFVSstability score: 0.7481 -> 0.8331Improved
add targeted adaptation to DIFRINTDIFRINT · BiTstability score: 0.7587 -> 0.7962Improved
add targeted adaptation to DMBVS on DOFVSDMBVS · DOFVSdistortion: 0.9531 -> 0.9061Hurt
add targeted adaptation to DIFRINTDIFRINT · NUSaverage persistence: 27.970 -> 36.254Improved

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