Research map / Video / Video generation
StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics
Bingliang Li, Zhenhong Sun, Jiaming Bian, Yuehao Wu, Yifu Wang, HONGDONG LI, Yatao Bian, Huadong Mo, Daoyi Dong
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 continuity memory graph (ablation) | StoryBlender · CineBoard3D | CIDS (Self): 0.547 -> 0.917 | Improved |
| add persistent asset registry M_asset (ablation) | StoryBlender · CineBoard3D | CIDS (Self): 0.532 -> 0.917 | Improved |
| share scene layout L_layout across shots (ablation) | StoryBlender · CineBoard3D | Spatial Drift Error: 4.12 -> 0.28 | Improved |
| share scene layout L_layout across shots (ablation) | StoryBlender · CineBoard3D | CIDS (Self): 0.908 -> 0.917 | No clear effect |
| add Visual Effects Artist agents (lighting, animation) (ablation) | StoryBlender · CineBoard3D | PA (Scene): 0.561 -> 3.176 | Improved |
| add Visual Effects Artist agents (ablation) | StoryBlender · CineBoard3D | PA (Action): 1.374 -> 2.629 | Improved |
| add story-centric reflection (5 iterations) (ablation) | StoryBlender · CineBoard3D | PA (Scene): 2.867 -> 3.176 | Improved |
| extend reflection from 3 to 5 iterations (ablation) | StoryBlender · CineBoard3D | PA (Scene): 3.114 -> 3.176 | Improved |
| use engine-verified physical reflection instead of naive LLM reflection (ablation) | Layout Artist · CineBoard3D layout errors | spatial errors | Improved |
| use 3D-grounded pipeline versus pixel-space Qwen-Edit | StoryBlender · CineBoard3D | PA (Scene): 3.736 -> 3.176 | Hurt |
| use 3D-grounded memory pipeline versus SceneWeaver | StoryBlender · CineBoard3D | CIDS (Self): 0.872 -> 0.917 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StoryDiffusion — StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation (NeurIPS 2024) · better on 2 of 2 shared results
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
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.88)
- LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization (ICLR 2026 · similarity 0.87)
- ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context (AAAI 2025 · similarity 0.87)
- Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds (NeurIPS 2026 · similarity 0.86)
- Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection (AAAI 2025 · similarity 0.86)
- Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling (ICLR 2025 · similarity 0.86)
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.
