Research map / Video / Video segmentation and tracking
A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Structural Awareness
Xiaoyi Feng, Tao Huang, Peng Wang, Zizhou Huang, Zhang Haihang, Yuntao Zou, Dagang Li, Kaifeng Zou
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 Gated Score Fusion with multiple keyframe references (ablation) | Ours · Paint Bucket dataset (S=3) | Acc: 0.8350 -> 0.8906 | Improved |
| add Gated Score Fusion with multiple keyframe references (ablation) | Ours · Industrial Animation dataset (S=3) | Acc: 0.7652 -> 0.8200 | Improved |
| add Gated Score Fusion with multiple keyframe references (ablation) | Ours · Paint Bucket dataset (S=5) | Acc: 0.6562 -> 0.7813 | Improved |
| add Gated Score Fusion with multiple keyframe references (ablation) | Ours · Industrial Animation dataset (S=5) | Acc: 0.6880 -> 0.7612 | Improved |
| add Gated Score Fusion with multiple keyframe references (ablation) | Ours · Paint Bucket dataset (S=10) | Acc: 0.5580 -> 0.6867 | Improved |
| add Gated Score Fusion with multiple keyframe references (ablation) | Ours · Industrial Animation dataset (S=10) | Acc: 0.6409 -> 0.7170 | Improved |
| add Multi-Scale Feature Matching module (ablation) | Ours · Paint Bucket dataset (S=3) | Acc: 0.8845 -> 0.8906 | Improved |
| add Multi-Scale Feature Matching module (ablation) | Ours · Industrial Animation dataset (S=3) | Acc: 0.8151 -> 0.8200 | Improved |
| add Multi-Scale Feature Matching module (ablation) | Ours · Paint Bucket dataset (S=5) | Acc: 0.7528 -> 0.7813 | Improved |
| add Multi-Scale Feature Matching module (ablation) | Ours · Industrial Animation dataset (S=5) | Acc: 0.7496 -> 0.7612 | Improved |
| add Multi-Scale Feature Matching module (ablation) | Ours · Paint Bucket dataset (S=10) | Acc: 0.6739 -> 0.6867 | Improved |
| add Multi-Scale Feature Matching module (ablation) | Ours · Industrial Animation dataset (S=10) | Acc: 0.7031 -> 0.7170 | Improved |
Closest papers by meaning
- Learning Inclusion Matching for Animation Paint Bucket Colorization (CVPR 2024 · similarity 0.90)
- Image Referenced Sketch Colorization Based on Animation Creation Workflow (CVPR 2025 · similarity 0.87)
- MangaNinja: Line Art Colorization with Precise Reference Following (CVPR 2025 · similarity 0.86)
- Automatic Controllable Colorization via Imagination (CVPR 2024 · similarity 0.84)
- AniDoc: Animation Creation Made Easier (CVPR 2025 · similarity 0.84)
- Prune and Repaint: Content-Aware Image Retargeting for any Ratio (NeurIPS 2024 · 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.
