AI Paper Atlas

Research map / Video / Video generation

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer

Qingyu Shi, Jianzong Wu, Jinbin Bai, Jiangning Zhang, Lu Qi, Yunhai Tong, Xiangtai Li

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 9 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
use shared temporal Conv1D kernel instead of LoRA (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Motion Fidelity: 80.4 -> 85.6Improved
use shared temporal Conv1D kernel instead of Local Attn (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Motion Fidelity: 73.1 -> 85.6Improved
use shared temporal Conv1D kernel instead of Conv3D (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Edit Fidelity: 27.1 -> 31.6Improved
add dense point tracking loss (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Motion Fidelity: 82.3 -> 85.6Improved
add dense point tracking loss (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Edit Fidelity: 31.2 -> 31.6Improved
drop temporal kernel in last 65% of layers instead of last 75% (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Motion Fidelity: 83.1 -> 85.6Improved
drop temporal kernel in last 65% of layers instead of last 55% (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Edit Fidelity: 30.4 -> 31.6Improved
kernel size 3 instead of 7 (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Motion Fidelity: 81.7 -> 85.6Improved
mid dim 128 instead of 256 (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Motion Fidelity: 82.6 -> 85.6Improved
lower denoising loss weight from 1.0 to 0.1 (ablation)DeT (CogVideoX-5B) · MTBench (30-video subset)Edit Fidelity: 31.6 -> 32.1Mixed
DeT vs MotionInversion on the same DiTCogVideoX-5B · MTBench (All)Edit Fidelity: 26.6 -> 31.2Improved
DeT vs MotionDirector (U-Net)DeT · MTBench (All)Motion Fidelity: 67.7 -> 85.8Improved

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