AI Paper Atlas

Research map / Video / Video generation

Tuning-free Visual Effect Transfer across Videos

Maxwell Jones, Rameen Abdal, Or Patashnik, Ruslan Salakhutdinov, Sergey Tulyakov, Jun-Yan Zhu, Kuan-Chieh Wang

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 4 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 reference effect video conditioning (ablation)RefVFX · Neural V2V user studyOverall Match win rate (%): 67.2 ± 2.9Improved
add reference effect video conditioning (ablation)RefVFX · Neural V2V user studyReference Video Adherence win rate (%): 57.5 ± 2.8Improved
add reference effect video conditioning (ablation)RefVFX · Code-based V2V user studyOverall Match win rate (%): 61.3 ± 3.9Improved
add reference effect video conditioning (ablation)RefVFX · I2V user studyOverall Match win rate (%): 61.8 ± 3.4Improved
add reference effect video conditioning (ablation)RefVFX · Neural V2V user studyInput Video Adherence win rate (%): 51.3 ± 3.1No clear effect
use RefVFX instead of Lucy EditRefVFX · Neural V2V user studyReference Video Adherence win rate (%): 62.3 ± 2.9Improved
use RefVFX instead of VACE PoseRefVFX · Neural V2V user studyInput Video Adherence win rate (%): 53.7 ± 2.2Improved
use RefVFX instead of VACE DepthRefVFX · Code-based V2V user studyReference Video Adherence win rate (%): 65.7 ± 5.4Improved
use RefVFX instead of Wan2.1 prompt-onlyRefVFX · I2V user studyReference Video Adherence win rate (%): 57.1 ± 2.4Improved
use RefVFX instead of Wan 2.1RefVFX · I2V similarityRef Sim (VideoPrism): 0.7230 -> 0.7378Improved
use RefVFX instead of Wan 2.1RefVFX · I2V similarityFirst Frame Sim (CLIP): 0.7911 -> 0.7698Hurt
use RefVFX instead of Lucy EditRefVFX · Neural V2V similarityRef Sim (VideoPrism): 0.6852 -> 0.7014Improved

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