Research map / Image generation / Editing and style transfer
Intuitive, Interactive Beard and Hair Synthesis With Generative Models
Kyle Olszewski, Duygu Ceylan, Jun Xing, Jose Echevarria, Zhili Chen, Weikai Chen, Hao Li
Check 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 the two-stage refinement and compositing pipeline rather than one network (ablation) | Facial hair synthesis · 100 challenging validation images | FID: 75.32 -> 53.15 | Improved |
| Add adversarial loss (ablation) | Facial hair synthesis · 100 challenging validation images | FID: 116.42 -> 53.15 | Improved |
| Add VGG perceptual loss (ablation) | Facial hair synthesis · 100 challenging validation images | FID: 67.82 -> 53.15 | Improved |
| Add synthetic training data alongside real images (ablation) | Facial hair synthesis · 100 challenging validation images | FID: 91.99 -> 53.15 | Improved |
| Add real-image training after synthetic-only training (ablation) | Facial hair synthesis · 100 challenging validation images | FID: 278.17 -> 53.15 | Improved |
| Use the proposed pipeline rather than the Isola et al. baseline | Facial hair synthesis · 100 challenging validation images | FID: 121.18 -> 53.15 | Improved |
| Use adversarial loss (ablation) | Facial hair synthesis · Qualitative ablation examples | fine-scale detail | Improved |
| Use VGG perceptual loss (ablation) | Facial hair synthesis · Qualitative ablation examples | noisy artifacts | Improved |
| Use the refinement network (ablation) | Facial hair synthesis · Qualitative ablation examples | boundary artifacts | Improved |
Closest papers by meaning
- Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (CVPR 2024 · similarity 0.89)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.89)
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 2024 · similarity 0.89)
- DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models (CVPR 2025 · similarity 0.89)
- MonoHair: High-Fidelity Hair Modeling from a Monocular Video (CVPR 2024 · similarity 0.88)
- DGH: Dynamic Gaussian Hair (NeurIPS 2025 · similarity 0.88)
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.
