Research map / Video / Video generation
MoCha: End-to-End Video Character Replacement without Structural Guidance
Zhengbo Xu, Jie Ma, Ziheng Wang, Zhan Peng, Jun Liang, Jing Li
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 |
|---|---|---|---|
| add the real-human datasets (expression-driven and augmented video-mask data) to rendered data (ablation) | MoCha · Qualitative, real-human cases | facial appearance and realism | Improved |
| add RL-based identity-enhancing post-training with reward LoRA (ablation) | MoCha · Qualitative | facial identity preservation | Improved |
| use single-frame mask without structural guidance instead of reconstruction-based paradigm | MoCha vs Wan-Animate · Synthetic benchmark | PSNR: 19.20 -> 23.09 | Improved |
| use MoCha instead of Wan-Animate | Wan-Animate · Synthetic benchmark | LPIPS: 0.213 -> 0.152 | Improved |
| use MoCha instead of VACE | VACE · Real-world VBench | Subject Consistency: 71.19 -> 92.25 | Improved |
| use MoCha instead of VACE | VACE · Real-world VBench | Imaging Quality: 60.88 -> 59.58 | Hurt |
| use MoCha instead of HunyuanCustom | HunyuanCustom · Real-world VBench | Temporal Flickering: 97.98 -> 97.98 | No clear effect |
| assign same RoPE frame index to source and target tokens and fixed index -1 to references (condition-aware RoPE) | MoCha · Design | flexibility | Improved |
Closest papers by meaning
- FaceShot: Bring Any Character into Life (ICLR 2025 · similarity 0.86)
- ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters (AAAI 2025 · similarity 0.85)
- FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation (NeurIPS 2026 · similarity 0.85)
- MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling (CVPR 2025 · similarity 0.85)
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024 · similarity 0.84)
- PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic Scenes (NeurIPS 2026 · similarity 0.84)
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.
