Research map / 3D vision / NeRF and radiance fields
Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images
Radu Alexandru Rosu, Shunsuke Saito, Ziyan Wang, Chenglei Wu, Sven Behnke, Giljoo Nam
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 |
|---|---|---|---|
| replace LMVS with Neural Strands for strand geometry (short hair) | LMVS · Synthetic short hair, 2mm/20deg | Recall (%): 30.29 -> 48.38 | Improved |
| replace LMVS with Neural Strands for strand geometry (short hair) | LMVS · Synthetic short hair, 3mm/30deg | F-score (%): 63.36 -> 82.75 | Improved |
| replace LMVS with Neural Strands for strand geometry (short hair) | LMVS · Synthetic short hair, 1mm/10deg | Precision (%): 56.91 -> 52.79 | Hurt |
| replace LMVS with Neural Strands (long hair) | LMVS · Synthetic long hair, 3mm/30deg | F-score (%): 68.47 -> 66.89 | Mixed |
| replace NeRF with Neural Strands | NeRF · Real hair novel views | LPIPS: 0.1598 -> 0.0811 | Improved |
| replace MVP with Neural Strands | MVP · Real hair novel views | LPIPS: 0.1226 -> 0.0811 | Improved |
| replace MVP with Neural Strands | MVP · Real hair novel views | PSNR: 32.82 -> 31.30 | Hurt |
| replace MVP with Neural Strands | MVP · Real hair novel views | SSIM: 0.9599 -> 0.9452 | Hurt |
| replace NeRF with Neural Strands | NeRF · Real hair rendering | total time (ms): 27,910 -> 73.36 | Improved |
| replace MVP with Neural Strands | MVP · Real hair rendering | total time (ms): 102.00 -> 73.36 | Improved |
| replace MVP with Neural Strands | MVP · Real hair rendering | decode time (ms): 20.40 -> 34.54 | Hurt |
| add coarse-to-fine and root-to-tip optimization of shape texture (ablation) | Neural Strands · Shape convergence | qualitative convergence | Improved |
Closest papers by meaning
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 2024 · similarity 0.92)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.91)
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments (CVPR 2024 · similarity 0.90)
- DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models (CVPR 2025 · similarity 0.90)
- Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (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.
