Research map / Image generation / Editing and style transfer
LOHO: Latent Optimization of Hairstyles via Orthogonalization
Rohit Saha, Brendan Duke, Florian Shkurti, Graham W. Taylor, Parham Aarabi
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 LOHO rather than MichiGAN for full-image hairstyle transfer | Hairstyle transfer on FFHQ · FFHQ test split, 5000 images | FID: 10.697 -> 8.419 | Improved |
| Use two-stage optimization rather than jointly optimizing all losses from the start (ablation) | LOHO · Hairstyle transfer | photorealism | Improved |
| Add gradient orthogonalization to the hair-structure loss gradient (ablation) | LOHO · Hair shape and structure transfer | IoU: 0.857 -> 0.932 | Improved |
| Add gradient orthogonalization to the hair-structure loss gradient (ablation) | LOHO · Hair shape and structure transfer, example 1 | IoU: 0.547 -> 0.603 | Improved |
| Add gradient orthogonalization to the hair-structure loss gradient (ablation) | LOHO · Hair shape and structure transfer, example 2 | IoU: 0.834 -> 0.857 | Improved |
| Add noise-map regularization (ablation) | LOHO · Hairstyle transfer | photorealism | Improved |
Later papers that compared with this method
2 later accepted papers report LOHO as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment (ECCV 2022 · better on 4 of 4 shared results)
- GAN with Multivariate Disentangling for Controllable Hair Editing (ECCV 2022 · 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
- HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach (NeurIPS 2024 · similarity 0.89)
- What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer (AAAI 2025 · similarity 0.87)
- Stable-Hair: Real-World Hair Transfer via Diffusion Model (AAAI 2025 · similarity 0.87)
- DGH: Dynamic Gaussian Hair (NeurIPS 2025 · similarity 0.87)
- HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion (NeurIPS 2024 · similarity 0.87)
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 2024 · similarity 0.86)
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.
