AI Paper Atlas

Research map / Video / Video generation

PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation

Hengjia Li, Haonan Qiu, Shiwei Zhang, Xiang Wang, Yujie Wei, Zekun Li, Yingya Zhang, Boxi Wu, Deng Cai

ICCV 2025 · Video › Video generation · approach: Compositional text-to-video diffusion · 22 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
tune on T2V model with direct video rewards instead of tuning on T2I model (ablation)PersonalVideo · Identity customization ablationID fidelityImproved
tune on T2V model instead of T2I model (ablation)PersonalVideo · Identity customization ablationbackground sharpness / semantic followingImproved
add simulated prompt augmentation (ablation)PersonalVideo · Identity customization ablationCLIP score / semantic followingImproved
add Semantic Consistency Reward (ablation)PersonalVideo · Identity customization ablationdynamic degreeImproved
add Semantic Consistency Reward (ablation)PersonalVideo · Identity customization ablationsemantic followingImproved
inject identity only in later denoising steps (last quarter) rather than all steps (ablation)PersonalVideo · Identity customization ablationmotion dynamicsImproved

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