AI Paper Atlas

Research map / Video / Video generation

Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

Wonjoon Jin, Jiyun Won, Janghyeok Han, Qi Dai, Chong Luo, Seung-Hwan Baek, Sunghyun Cho

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control

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 synthetic motion data to motion generator training (ablation)DynaVid · DynaVid-Human testFVD: +527.04 FVD without synthetic dataImproved
add synthetic motion data to motion generator training (ablation)DynaVid · PexelsFVD: -49.85 FVD without synthetic dataNo clear effect
mix real and synthetic flows in fine-tuning batches (ablation)DynaVid motion generator · PexelsFVD: +759.36 FVD without batch mixtureImproved
mix real and synthetic flows in fine-tuning batches (ablation)DynaVid motion generator · DynaVid-Human testFVD: -122.24 FVD without batch mixtureNo clear effect
filter real motion-video pairs by flow cycle consistency (1.19 px threshold) (ablation)DynaVid video generator · DynaVid-Human testM-Err: 4.734 -> 4.287Improved
filter real motion-video pairs by flow cycle consistency (ablation)DynaVid video generator · Pexels / DynaVid-HumanFVD, A-Qual: Pexels FVD -33.79 without filtering; DynaVid-Human +32.44No clear effect
train on rendered synthetic videos instead of synthetic motion (ablation)DynaVid · PexelsFVD: +104.43 FVD with rendered videosHurt
train on rendered synthetic videos instead of synthetic motion (ablation)DynaVid · DynaVid-Human testI-Qual: -0.0487 I-Qual; FVD -653.98 due to synthetic lookHurt
DynaVid versus Wan2.2-5B on dynamic human motionDynaVid · DynaVid-Human testFVD: 1775.99 -> 1351.94Improved
DynaVid versus AC3D on rapid camera motionDynaVid · DynaVid-Camera testmRotErr: 1.1529 -> 0.9289Improved
DynaVid versus GEN3C on common camera motionDynaVid · RE10K testmRotErr: 0.0809 (GEN3C) vs 0.1136Hurt
add Gaussian noise to input flow (25 to 5 dB) (ablation)motion-guided video generator · DynaVid-Human testA-Qual: 0.5312 -> 0.4632Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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