Research map / 3D vision / 3D generation
HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits
Leyang Jin, Yujian Zheng, Bingkui Tong, Yuda Qiu, Zhenyu Xie, Hao Li
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 full-view neural orientation extractor (vs Gabor filter) (ablation) | HairOrbit · Ablation, input view | HairSale (deg): 16.42 -> 12.83 | Improved |
| add full-view neural orientation extractor (vs Gabor filter) (ablation) | HairOrbit · Ablation, input view | IoU: 0.794 -> 0.847 | Improved |
| add full-view neural orientation extractor (vs Gabor filter) (ablation) | HairOrbit · Ablation, 8 synthesized views | HairSale (deg): 13.45 -> 9.97 | Improved |
| add scalp plus segment hybrid strand growing (vs scalp-only) (ablation) | HairOrbit · Ablation, input view | HairSale (deg): 13.70 -> 12.83 | Improved |
| add scalp plus segment hybrid strand growing (vs scalp-only) (ablation) | HairOrbit · Ablation, 8 synthesized views | IoU: 0.887 -> 0.900 | Improved |
| add multi-view bridging via synthesized views (vs single input view) (ablation) | HairOrbit · Ablation, input view | HairSale (deg): 19.10 -> 12.83 | Improved |
| add multi-view bridging via synthesized views (vs single input view) (ablation) | HairOrbit · Ablation, input view | IoU: 0.680 -> 0.847 | Improved |
| add multi-view bridging via synthesized views (vs single input view) (ablation) | HairOrbit · Ablation, 8 synthesized views | HairSale (deg): 24.14 -> 9.97 | Improved |
| use full-view orientation extractor instead of Gabor filter | orientation extraction · Full-view orientation (395 images) | mean angle error: 16.05 -> 5.13 | Improved |
| use undirected orientation target instead of HairStep directed strand map | orientation extraction · Full-view orientation (395 images) | mean angle error: 10.88 -> 5.13 | Improved |
| reformulate single-view as multi-view reconstruction vs Im2Haircut | HairOrbit · Single-view strand reconstruction | IoU: 0.757 -> 0.847 | Improved |
| reformulate single-view as multi-view reconstruction vs Im2Haircut | HairOrbit · Single-view strand reconstruction | HairSale (deg): 16.24 -> 12.83 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Im2Haircut — Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars (ICCV 2025) · better on 3 of 3 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
- MonoHair: High-Fidelity Hair Modeling from a Monocular Video (CVPR 2024 · similarity 0.91)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.90)
- DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models (CVPR 2025 · similarity 0.90)
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments (CVPR 2024 · similarity 0.90)
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 2024 · similarity 0.89)
- Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (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.
