Research map / 3D vision / Face and shape
3D Face Synthesis Driven by Personality Impression
Yining Lang, Wei Liang, Yujia Wang, Lap-Fai Yu
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 fine-tuned GoogLeNet instead of landmark features with an SVM | Personality impression classification · Personality impression classification | average accuracy: 75.3% -> 86.9% | Improved |
| Synthesize faces for a specified personality impression | Proposed 3D face synthesis · Synthesized faces, single personality impression | human recognition accuracy: 12.5% -> 38.0% | Improved |
| Use the data-driven sampler rather than randomly selecting and resetting an attribute | Face synthesis optimization · Example face optimization | total cost | Improved |
| Add facial expressions to synthesized faces | Proposed face synthesis · Synthesized faces with facial expressions | human recognition accuracy: 38% -> 33.4% | Hurt |
| Add an angry expression | Friendly synthesized face · Friendly face with angry expression | human recognition accuracy: 45.5% -> 30.0%; 15.5% | Hurt |
| Add an angry expression | Confident synthesized face · Confident face with angry expression | confident votes: 32.5% | No clear effect |
| Increase the similarity trade-off parameter from 0.3 to 0.5 | Face synthesis optimization · Hostile-looking face synthesis | similarity to input face: 0.3 -> 0.5 | Improved |
Closest papers by meaning
- Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation (AAAI 2020 · similarity 0.87)
- Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion (CVPR 2025 · similarity 0.87)
- Photo-Realistic Facial Details Synthesis From Single Image (ICCV 2019 · similarity 0.86)
- ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling (NeurIPS 2024 · similarity 0.85)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.84)
- PEGASUS: Personalized Generative 3D Avatars with Composable Attributes (CVPR 2024 · 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.
