Research map / Image generation / Editing and style transfer
MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing
Read the paperCheck 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 MangaGAN's artist-inspired geometry and region-wise translation | Frontal photo-to-manga translation · Photo-to-manga translation | visual quality | Helped |
| Add the structural smoothing loss (ablation) | MangaGAN eye and mouth translation · Eye and mouth regions | stroke-line cleanliness | Helped |
| Add the Similarity Preserving module (ablation) | MangaGAN eye and mouth translation · Eye and mouth regions | input-output similarity | Helped |
| Add the eye encoder (ablation) | MangaGAN eye translation · Eye regions | eye correspondence preservation | Helped |
| Add the mouth encoder and landmark-derived edge guidance (ablation) | MangaGAN mouth translation · Mouth regions | mouth correspondence preservation | Helped |
| Replace the Resnet 6-block generator with U-Net (ablation) | MangaGAN eye and mouth translation · Eye and mouth regions | visual quality | Hurt |
| Replace the Resnet 6-block generator with Resnet 9 blocks (ablation) | MangaGAN eye and mouth translation · Eye and mouth regions | visual quality | Hurt |
| Use MangaGAN rather than neural style transfer baselines | Photo-to-manga translation · Photo-to-manga translation | visual attractiveness | Helped |
| Use MangaGAN rather than cross-domain translation baselines | Photo-to-manga translation · Photo-to-manga translation | visual attractiveness | Helped |
Closest papers by meaning
- Invertible Conditional GAN Revisited: Photo-to-Manga Face Translation with Modern Architectures (Student Abstract) (AAAI 2023 · similarity 0.88)
- Region-Wise Correspondence Prediction between Manga Line Art Images (CVPR 2026 · similarity 0.87)
- CartoonGAN: Generative Adversarial Networks for Photo Cartoonization (CVPR 2018 · similarity 0.87)
- Advancing Manga Analysis: Comprehensive Segmentation Annotations for the Manga109 Dataset (CVPR 2025 · similarity 0.87)
- DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation (CVPR 2025 · similarity 0.85)
- DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors (CVPR 2024 · similarity 0.84)
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.