Research map / Image generation / Editing and style transfer
Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation
Rui Zhao, Wei Li, Zhipeng Hu, Lincheng Li, Zhengxia Zou, Zhenwei Shi, Changjie Fan
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 |
|---|---|---|---|
| fine-tune the pre-trained translator on text embeddings (ablation) | T2P without evolution search · 100 text prompts | CLIP Score: 27.29 ± 3.10 -> 34.85 ± 3.15 | Improved |
| add evolution search to a fine-tuned translator (ablation) | T2P · 100 text prompts | CLIP Score: 34.85 ± 3.15 -> 35.72 ± 2.70 | Improved |
| add a fine-tuned translator to evolution search (ablation) | T2P · 100 text prompts | CLIP Score: 35.31 ± 2.26 -> 35.72 ± 2.70 | Improved |
| combine translator fine-tuning with evolution search rather than using the fixed translator alone (ablation) | T2P · 100 text prompts | CLIP Score: 27.29 ± 3.10 -> 35.72 ± 2.70 | Improved |
| use T2P rather than DreamFusion | zero-shot game character creation · 24 text prompts | CLIP Ranking-1: 16.67% -> 66.66% | Improved |
| use T2P rather than AvatarCLIP | zero-shot game character creation · 24 text prompts | Reality: 1.97 ± 0.53 -> 3.87 ± 0.47 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DreamFusion — DreamFusion: Text-to-3D using 2D Diffusion (ICLR 2023) · better on 4 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting (CVPR 2025 · similarity 0.87)
- Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text (CVPR 2024 · similarity 0.83)
- StdGEN: Semantic-Decomposed 3D Character Generation from Single Images (CVPR 2025 · similarity 0.83)
- FaceShot: Bring Any Character into Life (ICLR 2025 · similarity 0.83)
- CharacterBench: Benchmarking Character Customization of Large Language Models (AAAI 2025 · similarity 0.83)
- DreamText: High Fidelity Scene Text Synthesis (CVPR 2025 · similarity 0.83)
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.
