Research map / Image generation / Editing and style transfer
Interactive Cartoonization With Controllable Perceptual Factors
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 |
|---|---|---|---|
| Separate texture and color into dedicated decoders | Cartooner · Cartoonization | perceptual quality | Helped |
| Apply recoloring before cartoonization instead of jointly modeling color and texture (ablation) | Cartooner · Cartoonization | color-control quality | Hurt |
| Apply recoloring after cartoonization instead of jointly modeling color and texture (ablation) | Cartooner · Cartoonization | cartoon-style color quality | Hurt |
| Train the stroke controller with only 2 levels instead of more stroke levels (ablation) | Cartooner · Stroke thickness control | stroke-thickness range | Hurt |
| Use more stroke levels during training (ablation) | Cartooner · Stroke thickness control | stroke-thickness range | Helped |
| Add network pre-training before full training (ablation) | Cartooner · Cartoonization | cartoonization quality | No clear effect |
| Use unshared convolution kernels in the abstraction controller (ablation) | Cartooner · Abstraction control | abstraction-transition consistency | Hurt |
| Use excessively expanded kernel sizes in the abstraction controller (ablation) | Cartooner · Abstraction control | perceptual quality | Hurt |
| Vary the abstraction-controller kernel sizes while keeping them in increasing order (ablation) | Cartooner · Abstraction control | output plausibility | No clear effect |
| Expand the generator receptive field without changing cartoon-image resolution (ablation) | Cartooner · Abstraction control | abstraction change | No clear effect |
| Expand the generator receptive field and increase cartoon-image resolution together (ablation) | Cartooner · Abstraction control | abstraction change | Helped |
| Add adversarial loss or regularization to the color module (ablation) | Cartooner color decoder · Color control | color quality | No clear effect |
Closest papers by meaning
- Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization (ICML 2022 · similarity 0.88)
- ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing (ICLR 2026 · similarity 0.87)
- Image Referenced Sketch Colorization Based on Animation Creation Workflow (CVPR 2025 · similarity 0.86)
- Automatic Controllable Colorization via Imagination (CVPR 2024 · similarity 0.86)
- MangaNinja: Line Art Colorization with Precise Reference Following (CVPR 2025 · similarity 0.85)
- Free-Lunch Color-Texture Disentanglement for Stylized Image Generation (NeurIPS 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.