Research map / Label-efficient and robust learning / Domain adaptation and generalization
ToonTalker: Cross-Domain Face Reenactment
Yuan Gong, Yong Zhang, Xiaodong Cun, Fei Yin, Yanbo Fan, Xuan Wang, Baoyuan Wu, 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 |
|---|---|---|---|
| add analogy constraint for unpaired cross-domain training (ablation) | ToonTalker · Cartoon->Real reenactment | FID: 43.353 -> 31.852 | Improved |
| add analogy constraint (ablation) | ToonTalker · Real->Cartoon reenactment | FID: 29.230 -> 28.531 | Improved |
| use query transformer instead of MLP (ablation) | ToonTalker · Real->Cartoon reenactment | FID: 116.740 -> 28.531 | Improved |
| use query transformer instead of MLP (ablation) | ToonTalker · Cartoon->Real reenactment | FID: 31.885 -> 31.852 | No clear effect |
| add spatial feature transformation (ablation) | ToonTalker generator · Cartoon->Real reenactment | FID: 41.077 -> 31.852 | Improved |
| add backward transformer (ablation) | ToonTalker · Cartoon->Real reenactment | FID: 35.265 -> 31.852 | Improved |
| increase motion-loss weight lambda_m from 0 to 100 (ablation) | ToonTalker · Real->Cartoon vs Cartoon->Real | FID: Real->Cartoon 26.885 -> 41.936; Cartoon->Real 33.463 -> 28.166 | Mixed |
| use ToonTalker instead of finetuned DaGAN/LIA/FOMM | cross-domain reenactment · Cartoon->Real reenactment | FID: 47.222 -> 31.852 | Improved |
| use ToonTalker in same-identity real-domain reconstruction | within-domain reenactment · VoxCeleb same-identity | AKD: 1.300 -> 1.335 | No clear effect |
| use ToonTalker in cross-identity real-domain reenactment | within-domain reenactment · Cross-identity real domain | CSIM: 0.548 -> 0.526 | No clear effect |
Closest papers by meaning
- FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features (CVPR 2024 · similarity 0.86)
- FaceShot: Bring Any Character into Life (ICLR 2025 · similarity 0.86)
- X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention (ICLR 2025 · similarity 0.85)
- ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters (AAAI 2025 · similarity 0.85)
- AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation (AAAI 2025 · similarity 0.85)
- RealPortrait: Realistic Portrait Animation with Diffusion Transformers (AAAI 2025 · 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.
