AI Paper Atlas

Research map / Video / Video generation

Generative Video Motion Editing with 3D Point Tracks

Yao-Chih Lee, Zhoutong Zhang, Jiahui Huang, Jui-Hsien Wang, Joon-Young Lee, Jia-Bin Huang, Eli Shechtman, Zhengqi Li

CVPR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 16 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
replace naive Gaussian-kernel sampling with cross-attention sampling/splatting (ablation)3D track conditioner · in-the-wild videosEPE: 16.18 -> 7.03Improved
use 3D tracks instead of 2D tracks (ablation)cross-attention conditioner · DyCheckPSNR: 13.88 -> 14.82Improved
use 3D tracks instead of 2D tracks (ablation)cross-attention conditioner · in-the-wild videosFVD: 305.93 -> 335.85Hurt
inject track z embeddings (ablation)3D track conditioner · in-the-wild videosEPE: 7.44 -> 6.12Improved
add real-data fine-tuning after synthetic training (ablation)Edit-by-Track · in-the-wild videosFVD: 623.32 -> 306.44Improved
add synthetic-data stage before real data (ablation)Edit-by-Track · in-the-wild videosEPE: 63.98 -> 6.12Improved
use two-stage training instead of single-stage mixed data (ablation)Edit-by-Track · in-the-wild videosFVD: 347.95 -> 306.44Improved
use Edit-by-Track instead of track-conditioned I2V ATIWan base · DyCheckLPIPS: 0.468 -> 0.406 (.468 -> .406)Improved
use 1.3B Edit-by-Track instead of 14B ATIWan · in-the-wild videosFVD: 268.80 -> 306.44Hurt
use 1.3B Edit-by-Track instead of 14B ATIWan · in-the-wild videosEPE: 11.44 -> 6.12Improved

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