Research map / Image generation / Editing and style transfer
Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 asymmetric cycle mapping with relaxed forward-cycle loss, local feature discriminators, and style control instead of CycleGAN | Portrait drawing generation · User study | Rank 1 percentage: 15.2% -> 68.5% | Helped |
| Use asymmetric cycle mapping with relaxed forward-cycle loss, local feature discriminators, and style control instead of ComboGAN | Portrait drawing generation · User study | Rank 1 percentage: 14.9% -> 68.5% | Helped |
| Use asymmetric cycle mapping with relaxed forward-cycle loss, local feature discriminators, and style control instead of LinearStyleTransfer | Portrait drawing generation · User study | Rank 1 percentage: 1.3% -> 68.5% | Helped |
| Remove relaxed cycle-consistency loss and local discriminators (ablation) | Proposed portrait drawing method · Portrait drawing generation | Facial feature preservation | Hurt |
| Remove relaxed cycle-consistency loss (ablation) | Proposed portrait drawing method · Portrait drawing generation | Facial feature preservation | Hurt |
| Remove local discriminators (ablation) | Proposed portrait drawing method · Portrait drawing generation | Facial feature quality | Hurt |
| Remove HED edge extraction from the relaxed cycle-consistency loss (ablation) | Proposed portrait drawing method · Portrait drawing generation | Line clarity and continuity | Hurt |
Closest papers by meaning
- PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup (CVPR 2018 · similarity 0.88)
- APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs (CVPR 2019 · similarity 0.87)
- DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis (CVPR 2024 · similarity 0.84)
- 3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images (CVPR 2024 · similarity 0.83)
- ACFun: Abstract-Concrete Fusion Facial Stylization (NeurIPS 2024 · similarity 0.83)
- ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image (AAAI 2025 · similarity 0.83)
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.