AI Paper Atlas

Research map / Video / Video generation

OSVE: One Step Video Editing with One Step Diffusion Models

Habin Lim, Gyeong-Moon Park

ECCV 2026 · Video › Video generation · approach: Diffusion-based video editing · 0 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 SAE loss to reconstruction loss for encoder training (ablation)OSVE encoder · PIE-Benchstructure distance: 0.087 -> 0.064Improved
add SAE loss to reconstruction loss (ablation)OSVE encoder · PIE-BenchCLIP Edit: 19.884 -> 20.416Improved
add reconstruction loss to SAE loss (ablation)OSVE encoder · PIE-BenchCLIP Whole: 22.349 -> 22.329No clear effect
add sliding window to UFE (ablation)OSVE · 90-frame videosSubject Consistency: 0.931 -> 0.954Improved
add anchor frame to UFE (ablation)OSVE · 90-frame videosSubject Consistency: 0.931 -> 0.943Improved
combine sliding window and anchor (ablation)OSVE · 90-frame videosBQS: 0.671 -> 0.677Improved
apply sliding window and anchor (UFE long video) (ablation)OSVE · 90-frame videosAesthetic Quality: 0.680 -> 0.670Hurt
use one-step OSVE instead of multi-step methodsOSVE · short videosBQS: 0.674 -> 0.679 (vs FRESCO)Improved
use one-step OSVE instead of RAVEOSVE · short videosFPS: 0.091 -> 15.625Improved
use one-step OSVE instead of RAVEOSVE · long videosFPS: 0.102 -> 15.793Improved
use OSVE vs best baseline in user studyOSVE · user studytemporal consistency: 3.68 -> 3.85Improved
OSVE vs Plug-and-Play and FRESCO on single metricsOSVE · short videosTemporal Flickering / Imaging Quality: TF 0.995 (PnP) vs 0.978; IQ 0.729 (FRESCO) vs 0.703Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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