Research map / 3D vision / Gaussian splatting
Human Hair Reconstruction with Strand-Aligned 3D Gaussians
Egor Zakharov, Vanessa Sklyarova, Michael J. Black, Giljoo Nam, Justus Thies, Otmar Hilliges
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 Gabor-filter orientation maps with Gaussian-lifted 3D orientation maps (ablation) | Gaussian Haircut · Synthetic hairstyles orientation maps | average angular error: 8° -> 7° | Improved |
| add the fine fitting step after coarse strand fitting (ablation) | Gaussian Haircut · Real-world scenes (qualitative) | hair geometry accuracy (qualitative) | Improved |
| add strand upsampling during coarse stage (ablation) | Gaussian Haircut · Real-world scenes (qualitative) | hair geometry accuracy (qualitative) | Improved |
| use the lifted 3D orientation maps instead of raw orientation maps (ablation) | Gaussian Haircut · Real-world scenes (qualitative) | geometry in poorly lit, entangled regions (qualitative) | Improved |
| include color, orientation and diffusion-based losses (ablation) | Gaussian Haircut · Real-world scenes close-ups (qualitative) | visual quality (qualitative) | Improved |
| replace Neural Haircut with Gaussian Haircut | strand-based hair reconstruction · Real-world monocular videos | optimization speed: more than ten times speed-up | Improved |
Closest papers by meaning
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments (CVPR 2024 · similarity 0.90)
- DGH: Dynamic Gaussian Hair (NeurIPS 2025 · 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 0.89)
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 2024 · similarity 0.88)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 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.
