AI Paper Atlas

Research map / Video / Video generation

Stylized Video Generation via Decoupled Data Synthesis and Gated Style Token Injection

Xin Wei, Yijie Fang, Yanjia Li, Liangyi Wu, Qin Yang, Mingrui Zhu, Nannan Wang, Xinbo Gao

ECCV 2026 · Video › Video generation · approach: Autoregressive long video generation · 0 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 clean style latent at timestep 0 instead of noisy (ablation)IGST · Style-guided T2V ablationCSD: 0.1490 -> 0.5219Improved
add head-wise gated attention (ablation)IGST · Style-guided T2V ablationCSD: 0.4530 -> 0.5219Improved
disable RoPE for style tokens (ablation)IGST · Style-guided T2V ablationCLIP text score: 0.2866 -> 0.3010Improved
add Diffusion-DPO post-training (ablation)IGST · Style-guided T2V ablationCSD: 0.4910 -> 0.5219Improved
add Diffusion-DPO post-training (ablation)IGST · Style-guided T2V ablationDynamic Degree: 0.7792 -> 0.8247Improved
use token concatenation instead of encoder-based explicit injection (ablation)IGST · Style-guided T2V ablationCSD: 0.3969 -> 0.5219Improved
train StyleMaster-style explicit injection on MoStyle-5K videos (ablation)StyleMaster · Style-guided T2V ablationDynamic Degree: 0.1710 -> 0.6472Improved
add image-video mixed training instead of video-only (ablation)IGST · Style-guided T2V ablationqualitative appearanceImproved
use IGST instead of StyleMasterIGST · Style-guided T2V ablationImage Quality: 0.6735 -> 0.6568Hurt
use IGST instead of StyleMasterIGST · Style-guided T2V ablationDynamic Degree: 0.1710 -> 0.8247Improved
use clean style latent (CLIP text score) (ablation)IGST · Style-guided T2V ablationCLIP text score: 0.3144 -> 0.3010Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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