Research map / Video / Video generation
DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use DPE for expression editing instead of PIRenderer | DPE · Same-Identity Reenactment | AED: 0.1205 -> 0.1133 | Helped |
| Use DPE for expression editing instead of PIRenderer | DPE · Cross-Identity Reenactment | CSIM: 0.9133 -> 0.9204 | Helped |
| Use DPE for expression editing instead of PIRenderer | DPE · Same-Identity Reenactment | APD: 0.01254 -> 0.01720 | Hurt |
| Use DPE for expression editing instead of PIRenderer | DPE · Cross-Identity Reenactment | APD: 0.01182 -> 0.02464 | Hurt |
| Use DPE for pose editing instead of PIRenderer | DPE · Same-Identity Reenactment | CSIM: 0.9055 -> 0.9192 | Helped |
| Use DPE for pose editing instead of PIRenderer | DPE · Cross-Identity Reenactment | AED: 0.1397 -> 0.1250 | Helped |
| Use DPE for pose editing instead of PIRenderer | DPE · Cross-Identity Reenactment | APD: 0.02533 -> 0.03630 | Hurt |
| Use DPE for one-shot reenactment instead of competing methods | DPE · Same-Identity Reenactment | PSNR: 31.1134 -> 31.3631 | Helped |
| Use DPE for one-shot reenactment instead of competing methods | DPE · Cross-Identity Reenactment | CSIM: 0.8215 -> 0.8303 | Helped |
| Add the expression-generator refinement training stage (ablation) | DPE · Video portrait editing | visual quality | Helped |
| Add the self-reconstruction constraint (ablation) | DPE · Video portrait editing | visual quality | Helped |
Closest papers by meaning
- FG-EmoTalk: Talking Head Video Generation with Fine-Grained Controllable Facial Expressions (AAAI 2024 · similarity 0.88)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.88)
- Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation (CVPR 2025 · similarity 0.88)
- Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis (ICLR 2024 · similarity 0.87)
- VOODOO 3D: Volumetric Portrait Disentanglement For One-Shot 3D Head Reenactment (CVPR 2024 · similarity 0.87)
- Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation (AAAI 2025 · similarity 0.87)
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.