Research map / Image generation / Editing and style transfer
Neural Hair Rendering
Menglei Chai, Jian Ren, Sergey Tulyakov
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 shared latent space (shared encoder layers) (ablation) | Ours w/o SL and SD (structure discriminator removed) · FFHQ hair rendering | FID: 94.25 -> 77.09 | Improved |
| add shared latent space (shared encoder layers) (ablation) | Ours w/o SL and SD · FFHQ hair rendering | IoU (%): 80.10 -> 86.60 | Improved |
| add structure discriminator (ablation) | Ours w/o SD · FFHQ hair rendering | FID: 77.09 -> 57.08 | Improved |
| add structure discriminator (ablation) | Ours w/o SD · FFHQ hair rendering | IoU (%): 86.60 -> 86.74 | Improved |
| add structure discriminator (ablation) | Ours w/o SD · FFHQ hair rendering | Pixel accuracy (%): 96.35 -> 96.45 | Improved |
| replace graphic renderer with the neural pipeline | Graphic Renderer · FFHQ hair rendering | FID: 98.62 -> 57.08 | Improved |
| replace graphic renderer with the neural pipeline | Graphic Renderer · FFHQ hair rendering | IoU (%): 55.77 -> 86.74 | Improved |
| use proposed method instead of CycleGAN | CycleGAN · FFHQ hair rendering | FID: 107.11 -> 57.08 | Improved |
| use proposed method instead of UNIT | UNIT · FFHQ hair rendering | IoU (%): 30.89 -> 86.74 | Improved |
| use proposed method instead of DRIT | DRIT · FFHQ hair rendering | Pixel accuracy (%): 65.80 -> 96.45 | Improved |
| add temporal conditioning with warped previous frame (ablation) | Ours · FFHQ hair rendering | temporal consistency (qualitative) | 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.
- DRIT — DRIT++: Diverse Image-to-Image Translation via Disentangled Representations (IJCV 2020) · 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
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.90)
- MonoHair: High-Fidelity Hair Modeling from a Monocular Video (CVPR 2024 · similarity 0.89)
- Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (CVPR 2024 · similarity 0.89)
- HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach (NeurIPS 2024 · similarity 0.89)
- DGH: Dynamic Gaussian Hair (NeurIPS 2025 · similarity 0.88)
- Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation (NeurIPS 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.
