Research map / 3D vision / Face and shape
NeuralHDHair: Automatic High-Fidelity Hair Modeling From a Single Image Using Implicit Neural Representations
Keyu Wu, Yifan Ye, Lingchen Yang, Hongbo Fu, Kun Zhou, Youyi Zheng
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 NeuralHDHair instead of PIFuHD | Monocular hair reconstruction · Synthetic data | Precision(%): 71.08 -> 76.36 | Improved |
| use NeuralHDHair instead of Dynamic Hair | Monocular hair reconstruction · Synthetic data | L2: 0.1293 -> 0.1040 | Improved |
| use NeuralHDHair instead of Dynamic Hair | Monocular hair reconstruction · Real data | L1: 0.2091 -> 0.1458 | Improved |
| use NeuralHDHair instead of Dynamic Hair | Monocular hair reconstruction · Real data | User study(%): 19.38 -> 65.67 | Improved |
| replace the traditional hair-growth algorithm with GrowingNet | Hair growth · Hair growth | Time(s): 10.57 -> 1.21 | Improved |
| remove the overlapping latent patch scheme (ablation) | GrowingNet · Hair growth | Time(s): 1.21 -> 0.25 | Improved |
| remove the overlapping latent patch scheme (ablation) | GrowingNet · Hair growth | strand continuity | Hurt |
| remove the IRHairNet fine module (ablation) | IRHairNet · Hair reconstruction | local detail fidelity | Hurt |
| remove the implicit toVoxel module (VIFu) (ablation) | IRHairNet · Hair reconstruction | geometric fidelity | Hurt |
| use luminance map alone instead of complementing the orientation map (ablation) | IRHairNet · Hair reconstruction | generalization | Hurt |
| reduce local patch size to 4 (ablation) | GrowingNet · Hair growth | Time(s): 1.21 -> 5.75 | Hurt |
| increase local patch size to 32 (ablation) | GrowingNet · Hair reconstruction | modeling detail accuracy | Hurt |
Later papers that compared with this method
1 later accepted paper reports NeuralHDHair as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars (ICCV 2025 · better on 2 of 2 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
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 2024 · similarity 0.91)
- DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models (CVPR 2025 · similarity 0.91)
- MonoHair: High-Fidelity Hair Modeling from a Monocular Video (CVPR 2024 · similarity 0.90)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.90)
- DGH: Dynamic Gaussian Hair (NeurIPS 2025 · similarity 0.90)
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments (CVPR 2024 · 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.
