AI Paper Atlas

Research map / Video / Video generation

AnyI2V: Animating Any Conditional Image with Motion Control

Ziye Li, Hao Luo, Xincheng Shuai, Henghui Ding

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 8 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 K&V consistency across frames (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)FVD: 587.69 -> 569.89Improved
add K&V consistency across frames (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)ObjMC: 16.81 -> 16.39Improved
add PCA reduction of query features (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)ObjMC: 17.14 -> 16.39Improved
add PCA reduction of query features (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)FVD: 585.04 -> 569.89Improved
add semantic mask instead of static mask (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)FVD: 598.15 -> 569.89Improved
add semantic mask instead of static mask (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)ObjMC: 16.92 -> 16.39Improved
add semantic mask (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)ObjMC: 17.62 -> 16.39Improved
align query instead of residual hidden for latent optimization (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)ObjMC: 36.23 -> 16.39Improved
align query instead of residual hidden for latent optimization (ablation)AnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)FID: 129.40 -> 104.53Improved
use AnyI2V training-free control instead of AnimateDiff + SparseCtrl baselineAnimateDiff · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)ObjMC: 38.26 -> 16.39Improved
use AnyI2V instead of best training-free ObjCtrl-2.5DAnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)FID: 111.82 -> 104.53Improved
compare with trained DragAnythingAnyI2V · Trajectory-controlled I2V (web + VIPSeg, structural condition first frame)ObjMC: 13.60 vs 16.39Hurt

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