Research map / Image generation / Editing and style transfer
Face-to-Parameter Translation for Game Character Auto-Creation
Tianyang Shi, Yi Yuan, Changjie Fan, Zhengxia Zou, Zhenwei Shi, Yong Liu
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 facial content loss L2 to the discriminative loss (ablation) | F2P face-to-parameter translation · Subjective evaluation (selection ratio) | selection ratio: 13.47% -> 50.26% | Improved |
| add discriminative loss L1 to the facial content loss (ablation) | F2P face-to-parameter translation · Subjective evaluation (selection ratio) | selection ratio: 36.27% -> 50.26% | Improved |
| add discriminative loss on top of Gatys content loss baseline (ablation) | F2P face-to-parameter translation · Celebrity dataset, face recognition cosine similarity | cosine similarity | Improved |
| add facial content loss (ablation) | F2P face-to-parameter translation · Celebrity dataset, edge-map alignment | pixel correspondence of facial edges | Improved |
| use F2P instead of Global style transfer | game character creation · Celebrity dataset | Frechet Inception Distance: 0.0677 -> 0.0390 | Improved |
| use F2P instead of Local style transfer | game character creation · Celebrity dataset | Mode Score: 1.0316 -> 1.1418 | Improved |
| use F2P instead of Local style transfer | game character creation · Celebrity dataset | runtime: 43s -> 16s | Improved |
| apply method to blurred and varied-illumination photos or pose changes | F2P · robustness tests | qualitative quality | Mixed |
Closest papers by meaning
- Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation (AAAI 2020 · similarity 0.95)
- EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting (CVPR 2025 · similarity 0.89)
- GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer (NeurIPS 2025 · similarity 0.83)
- FaceShot: Bring Any Character into Life (ICLR 2025 · similarity 0.83)
- G2L-CariGAN: Caricature Generation from Global Structure to Local Features (AAAI 2024 · similarity 0.82)
- StdGEN: Semantic-Decomposed 3D Character Generation from Single Images (CVPR 2025 · similarity 0.82)
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.
