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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| tune on T2V model with direct video rewards instead of tuning on T2I model (ablation) | PersonalVideo · Identity customization ablation | ID fidelity | Improved |
| tune on T2V model instead of T2I model (ablation) | PersonalVideo · Identity customization ablation | background sharpness / semantic following | Improved |
| add simulated prompt augmentation (ablation) | PersonalVideo · Identity customization ablation | CLIP score / semantic following | Improved |
| add Semantic Consistency Reward (ablation) | PersonalVideo · Identity customization ablation | dynamic degree | Improved |
| add Semantic Consistency Reward (ablation) | PersonalVideo · Identity customization ablation | semantic following | Improved |
| inject identity only in later denoising steps (last quarter) rather than all steps (ablation) | PersonalVideo · Identity customization ablation | motion dynamics | Improved |
Closest papers by meaning
- Identity-Preserving Text-to-Video Generation by Frequency Decomposition (CVPR 2025 · similarity 0.89)
- ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation (NeurIPS 2026 · similarity 0.88)
- FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation (NeurIPS 2026 · similarity 0.87)
- PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement (NeurIPS 2025 · similarity 0.87)
- Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts (CVPR 2025 · similarity 0.87)
- VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models (CVPR 2025 · similarity 0.86)
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.
