Research map / 3D vision / Face and shape
Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction
Vanessa Sklyarova, Jenya Chelishev, Andreea Dogaru, Igor Medvedev, Victor Lempitsky, Egor Zakharov
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 the rendering mask loss L_mask (soft silhouette) to the strand fitting (ablation) | Neural Haircut strand fitting · Synthetic hair (Cem Yuksel models) | recall / F-score | Improved |
| use the full objective L_fine (geometry + rendering + diffusion prior) instead of rendering losses alone (ablation) | Neural Haircut strand fitting · Synthetic hair (Cem Yuksel models) | recall / F-score | Improved |
| add the photometric rendering loss L_rgb (ablation) | Neural Haircut strand fitting · Synthetic hair (curly and straight) | precision / F-score | Improved |
| add the one-way chamfer loss L_chm (ablation) | Neural Haircut geometry loss · Synthetic hair | qualitative coverage | Improved |
| add the volume loss L_vol (ablation) | Neural Haircut geometry loss · Synthetic hair | qualitative realism | Improved |
| add the orientation loss L_orient (ablation) | Neural Haircut geometry loss · Synthetic hair | qualitative realism | Improved |
| add the diffusion-based hairstyle prior L_prior (ablation) | Neural Haircut strand fitting · Real-world hair (qualitative) | realism of inner hairstyle | Improved |
| add the curvature loss term to the strand parametric model (ablation) | Strand VAE · Curly hairstyles (qualitative) | curly hair fidelity | Improved |
| vary soft rasterization faces per pixel and batch size away from 16 and 1 (ablation) | Soft hair rasterizer · Curly synthetic hair | reconstruction metrics | No clear effect |
| compare against re-implemented Neural Strands with the same geometry loss | Neural Haircut vs Neural Strands* · Synthetic hair | precision / recall / F-score | Improved |
Closest papers by meaning
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments (CVPR 2024 · similarity 0.92)
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 2024 · similarity 0.91)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.91)
- MonoHair: High-Fidelity Hair Modeling from a Monocular Video (CVPR 2024 · similarity 0.90)
- DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models (CVPR 2025 · similarity 0.89)
- Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (CVPR 2024 · similarity 0.89)
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.
