Research map / Video / Video generation
FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
Xiangyang Luo, Qingyu Li, Xiaokun Liu, Wenyu Qin, Miao Yang, Meng Wang, Pengfei Wan, Di Zhang, Kun Gai, Shao-Lun Huang
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 Shot Cache (ablation) | FilmWeaver · Multi-shot eval set | Consistency All (%): 65.44 -> 75.12 | Improved |
| add Shot Cache (ablation) | FilmWeaver · Multi-shot eval set | Consistency Char. (%): 68.11 -> 74.61 | Improved |
| add Shot Cache (ablation) | FilmWeaver · Multi-shot eval set | Aesthetics Score: 33.92 -> 33.69 | No clear effect |
| add Temporal Cache (ablation) | FilmWeaver · Multi-shot eval set | Consistency All (%): 70.57 -> 75.12 | Improved |
| add Temporal Cache (ablation) | FilmWeaver · Multi-shot eval set | Aesthetics Score: 31.61 -> 33.69 | Improved |
| add Temporal Cache (ablation) | FilmWeaver · Multi-shot eval set | Text Alignment Char.: 20.21 -> 23.07 | Improved |
| add noise augmentation (ablation) | FilmWeaver · Multi-shot eval set | Text Alignment All: 28.12 -> 31.23 | Improved |
| add noise augmentation (ablation) | FilmWeaver · Multi-shot eval set | Aesthetics Score: 30.04 -> 33.69 | Improved |
| add noise augmentation (ablation) | FilmWeaver · Multi-shot eval set | Consistency All (%): 75.92 -> 75.12 | No clear effect |
| FilmWeaver vs StoryDiffusion (ablation) | FilmWeaver · Multi-shot eval set | Aesthetics Score: 35.61 vs 33.69 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- StoryDiffusion — StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation (NeurIPS 2024) · better on 4 of 5 shared results
- VideoStudio — VideoStudio: Generating Consistent-Content and Multi-Scene Videos (ECCV 2024) · better on 5 of 5 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
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text (CVPR 2025 · similarity 0.89)
- MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences (ICLR 2025 · similarity 0.88)
- ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models (CVPR 2025 · similarity 0.88)
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception (NeurIPS 2025 · similarity 0.88)
- EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation (NeurIPS 2026 · similarity 0.88)
- MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation (CVPR 2025 · similarity 0.88)
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.
