Research map / 3D vision / Face and shape
Learning to Caricature via Semantic Shape Transform
Wenqing Chu, Wei-Chih Hung, Yi-Hsuan Tsai, Yu-Ting Chang, Yijun Li, Deng Cai, Ming–Hsuan Yang
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 reconstruction loss L_rec (ablation) | semantic shape transformation · WebCaricature shape transformation | mIoU: 23.25 -> 61.66 | Improved |
| add adversarial loss L_adv (ablation) | semantic shape transformation · WebCaricature shape transformation | mIoU: 58.19 -> 61.66 | Improved |
| add cycle consistency loss L_cyc (ablation) | semantic shape transformation · WebCaricature shape transformation | mIoU: 58.42 -> 61.66 | Improved |
| add coordinate-based loss L_coo (ablation) | semantic shape transformation · WebCaricature shape transformation | mIoU: 60.05 -> 61.66 | Improved |
| add coordinate-based loss L_coo (ablation) | semantic shape transformation · WebCaricature shape transformation | pixAcc: 95.49 -> 95.60 | Improved |
| use learned semantic parsing-map model instead of non-rigid registration | shape transformation · WebCaricature shape transformation | mIoU: 46.5 -> 61.7 | Improved |
| use learned model instead of Neural Best-Buddies | shape transformation · WebCaricature shape transformation | pixAcc: 61.7 -> 95.6 | Improved |
| use parsing maps instead of landmark polygons as input (ablation) | caricature generation · WebCaricature user study | preference: 89% of 310 votes prefer ours | Improved |
| use retrieved caricature references instead of random references (ablation) | deformed photos · WebCaricature user study | preference: 83% of 900 pairwise outcomes | Improved |
| use proposed method instead of WarpGAN | caricature generation · identity preservation study | accuracy: 68% -> 70% | Improved |
| use proposed method instead of CariGAN | caricature generation · identity preservation study | accuracy: 53% -> 70% | Improved |
Closest papers by meaning
- CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth (CVPR 2025 · similarity 0.88)
- Alive Caricature From 2D to 3D (CVPR 2018 · similarity 0.88)
- WarpGAN: Automatic Caricature Generation (CVPR 2019 · similarity 0.87)
- 3DCaricShop: A Dataset and a Baseline Method for Single-View 3D Caricature Face Reconstruction (CVPR 2021 · similarity 0.87)
- DemoCaricature: Democratising Caricature Generation with a Rough Sketch (CVPR 2024 · similarity 0.85)
- G2L-CariGAN: Caricature Generation from Global Structure to Local Features (AAAI 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.
