Research map / Video / Video generation
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
Fei Yin, Yong Zhang, Xiaodong Cun, Mingdeng Cao, Yanbo Fan, Xuan Wang, Qingyan Bai, Baoyuan Wu, Jue Wang, Yujiu Yang
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 |
|---|---|---|---|
| use pre-trained StyleGAN feature-space warping instead of image-space refinement (Ours vs PIRenderer) | StyleHEAT · Same-identity reenactment | FID: 27.14 -> 18.02 | Improved |
| StyleHEAT vs PIRenderer on cross-identity reenactment | StyleHEAT · Cross-identity reenactment | FID: 108.56 -> 91.28 | Improved |
| StyleHEAT vs PIRenderer on cross-identity identity similarity | StyleHEAT · Cross-identity reenactment | CSIM: 0.4812 -> 0.4890 | Improved |
| StyleHEAT vs FOMM on same-identity identity similarity (GAN inversion loses identity) | StyleHEAT · Same-identity reenactment | CSIM: 0.8121 -> 0.7475 | Hurt |
| StyleHEAT vs PIRenderer on motion accuracy (AED/APD) | StyleHEAT · Same-identity reenactment | AED: 0.1073 -> 0.1151 | No clear effect |
| add calibration network to feature warping (ablation) | StyleHEAT · Qualitative ablation | visual quality (teeth, closed eyes) | Improved |
| add domain loss on calibrated feature maps (ablation) | StyleHEAT · Qualitative ablation | visual quality (detail) | Improved |
Closest papers by meaning
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.91)
- Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation (CVPR 2025 · similarity 0.90)
- Enhancing Identity-Deformation Disentanglement in StyleGAN for One-Shot Face Video Re-Enactment (AAAI 2025 · similarity 0.89)
- FG-EmoTalk: Talking Head Video Generation with Fine-Grained Controllable Facial Expressions (AAAI 2024 · similarity 0.89)
- Say Anything with Any Style (AAAI 2024 · similarity 0.89)
- OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking (NeurIPS 2025 · similarity 0.89)
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.
