Research map / Image generation / Editing and style transfer
Unpaired Cartoon Image Synthesis via Gated Cycle Mapping
Yifang Men, Yuan Yao, Miaomiao Cui, Zhouhui Lian, Xuansong Xie, Xian-Sheng Hua
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 gated cycle mapping instead of the strongest listed baseline | Cartoon image synthesis · selfie2anime | FID: 89.51 -> 79.74 | Improved |
| Use gated cycle mapping instead of the strongest listed baseline | Cartoon image synthesis · selfie2anime | KID×100: 2.36±0.23 -> 1.59±0.25 | Improved |
| Use gated cycle mapping instead of the strongest listed baseline | Cartoon image synthesis · scene2cartoon | FID: 255.85 -> 253.83 | Improved |
| Use gated cycle mapping instead of the strongest listed baseline | Cartoon image synthesis · scene2cartoon | KID×100: 6.19±0.74 -> 6.40±0.73 | No clear effect |
| Add style guidance from a reference exemplar (ablation) | Gated cycle mapping · cartoon image synthesis | visual quality and geometry transfer | Improved |
| Add domain-specific layers to the gated mapping unit (ablation) | Gated cycle mapping · cartoon image synthesis | category-specific style quality | Improved |
| Add group-specific layers to the gated mapping unit (ablation) | Gated cycle mapping · portrait and scene cartoonization | category-specific style quality | Improved |
| Add the style reconstruction loss Lsty (ablation) | Gated cycle mapping · cartoon image synthesis | reference-style coherence | Improved |
| Add the diverse style loss Lds (ablation) | Gated cycle mapping · cartoon image synthesis | style diversity | Improved |
| Replace diverse style loss with adaptive style loss for same-class references (ablation) | Video extension of gated cycle mapping · cartoon portrait video synthesis | facial-expression consistency | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- U-GAT-IT — U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020) · better on 2 of 2 shared results
- DRIT++ — DRIT++: Diverse Image-to-Image Translation via Disentangled Representations (IJCV 2020) · better on 2 of 2 shared results
- CartoonGAN — CartoonGAN: Generative Adversarial Networks for Photo Cartoonization (CVPR 2018) · better on 1 of 1 shared result
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
- CartoonGAN: Generative Adversarial Networks for Photo Cartoonization (CVPR 2018 · similarity 0.86)
- Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation (ICCV 2023 · similarity 0.86)
- Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks (ICCV 2017 · similarity 0.86)
- ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing (ICLR 2026 · similarity 0.86)
- Unaligned Image-to-Image Translation by Learning to Reweight (ICCV 2021 · similarity 0.85)
- ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis (NeurIPS 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.
