ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
Xiaoxue Wu, Xinyuan Chen, Yaohui Wang, Yu Qiao
摘要
Shot transitions play a pivotal role in multi-shot video generation, as they determine the overall narrative expression and the directorial design of visual storytelling.However, recent progress has primarily focused on low-level visual consistency across shots, neglecting how transitions are designed and how cinematographic language contributes to coherent narrative expression. This often leads to mere sequential shot changes without intentional film-editing patterns. To address this limitation, we propose ShotDirector, an efficient framework that integrates parameter-level camera control and hierarchical editing-pattern-aware prompting.Specifically, we adopt a camera control module that incorporates 6-DoF poses and intrinsic settings to enable precise camera information injection. In addition, a shot-aware mask mechanism is employed to introduce hierarchical prompts aware of professional editing patterns, allowing fine-grained control over shot content. Through this design, our framework effectively combines parameter-level conditions with high-level semantic guidance, achieving film-like controllable shot transitions.To facilitate training and evaluation, we construct ShotWeaver40K, a dataset that captures the priors of film-like editing patterns, and develop a set of evaluation metrics for controllable multi-shot video generation. Extensive experiments demonstrate the effectiveness of our framework.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper32
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 被引用 18,833 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 被引用 5,568 次
相关 Paper
- MultiShotMaster: A Controllable Multi-Shot Video Generation FrameworkQinghe Wang, Xiaoyu Shi, Baolu Li, Weikang Bian 等CVPR 2026 · 被引用 33 次
- CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion ModelsXiaoxue Wu, Bingjie Gao, Yu Qiao, Yaohui Wang 等ICLR 2026 · 被引用 26 次
- STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot NarrativePeixuan Zhang, Zijian Jia, Kaiqi Liu, Shuchen Weng 等CVPR 2026 · 被引用 25 次
- FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive DiffusionXiangyang Luo, Qingyu Li, Xiaokun Liu, Wenyu Qin 等AAAI 2026 · 被引用 3 次
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language ModelsHongbo Liu, Jingwen He, Yi Jin, Dian Zheng 等NeurIPS 2025 · 被引用 24 次
