Research map / Video / Video generation
ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
Xiaoxue Wu, Xinyuan Chen, Yaohui Wang, Yu Qiao
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-aware mask (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Transition confidence: 0.7572 -> 0.8956 | Improved |
| add shot-aware mask (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Semantic consistency: 0.7183 -> 0.7918 | Improved |
| add visual shot-aware mask (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Transition confidence: 0.8044 -> 0.8956 | Improved |
| add semantic shot-aware mask (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Semantic consistency: 0.6901 -> 0.7918 | Improved |
| add semantic shot-aware mask (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Transition confidence: 0.8913 -> 0.8956 | No clear effect |
| train on ShotWeaver40K (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Transition confidence: 0.1402 -> 0.8956 | Improved |
| train on ShotWeaver40K (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Semantic consistency: 0.8419 -> 0.7918 | Hurt |
| add stage II training with SynCamVideo (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | Transition confidence: 0.8615 -> 0.8956 | Improved |
| add stage II training with SynCamVideo (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | FVD: 68.97 -> 68.45 | Improved |
| add camera information injection (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | RotErr: 0.6330 -> 0.5907 | Improved |
| add camera information injection (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | TransErr: 0.5740 -> 0.5393 | Improved |
| add Plücker branch (ablation) | ShotDirector · ShotWeaver eval (90 prompts) | RotErr: 0.6262 -> 0.5907 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.
- Mask2DiT — Mask^2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation (CVPR 2025) · better on 3 of 3 shared results
- ReCamMaster — ReCamMaster: Camera-Controlled Generative Rendering from A Single Video (ICCV 2025) · better on 3 of 3 shared results
- SynCamMaster — SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints (ICLR 2025) · better on 1 of 2 shared results
- StoryDiffusion — StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation (NeurIPS 2024) · better on 1 of 1 shared result
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
- Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation (NeurIPS 2025 · similarity 0.87)
- CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation (NeurIPS 2025 · similarity 0.87)
- ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models (CVPR 2025 · similarity 0.86)
- Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation (NeurIPS 2026 · similarity 0.86)
- CCEdit: Creative and Controllable Video Editing via Diffusion Models (CVPR 2024 · similarity 0.86)
- CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation (NeurIPS 2026 · 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.
