Research map / Video / Video generation
Character-Preserving Coherent Story Visualization
Yun-Zhu Song, Zhi Rui Tam, Hung-Jen Chen, Huiao-Han Lu, Hong-Han Shuai
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 |
|---|---|---|---|
| replace baseline with CP-CSV (add figure-ground segmentation, parallel, layers 1,2) (ablation) | StoryGAN baseline · Pororo-SV | FSD: 98.61 -> 72.60 | Improved |
| add figure-ground segmentation in parallel at layers 1,2 (ablation) | baseline · Pororo-SV | FID: 74.60 -> 69.55 | Improved |
| add figure-ground segmentation in parallel at layers 1,2 (ablation) | baseline · Pororo-SV | FVD: 189.46 -> 177.27 | Improved |
| add cascade segmentation instead of parallel (ablation) | baseline · Pororo-SV | FSD: 98.61 -> 86.80 | Improved |
| fuse segmentation at all layers k=1,2,3,4 instead of 1,2 (ablation) | CP-CSV · Pororo-SV | FID: 69.55 -> 84.41 | Hurt |
| fuse segmentation at later layers k=3,4 instead of 1,2 (ablation) | CP-CSV · Pororo-SV | FSD: 72.60 -> 99.66 | Hurt |
| fuse segmentation at later layers k=3,4 instead of 1,2 (ablation) | CP-CSV · Pororo-SV | FID: 69.55 -> 80.54 | Hurt |
| use cascade generation instead of parallel (ablation) | CP-CSV · Pororo-SV | FSD: 72.60 -> 86.80 | Hurt |
| CP-CSV vs StoryGAN | StoryGAN · Pororo-SV | FID: 77.67 -> 67.76 | Improved |
| CP-CSV vs StoryGAN | StoryGAN · Pororo-SV | FVD: 274.59 -> 190.59 | Improved |
| CP-CSV vs StoryGAN | StoryGAN · Pororo-SV | FSD: 111.09 -> 71.51 | Improved |
| FSD instead of FVD as perturbation-sensitive metric | FVD · Pororo-SV Inter-S shuffle | Pearson correlation: 0.9671 -> 0.9984 | Improved |
Closest papers by meaning
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.90)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.88)
- ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context (AAAI 2025 · similarity 0.88)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.87)
- Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models (AAAI 2025 · similarity 0.87)
- StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization (AAAI 2025 · similarity 0.87)
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.
