Yingshuang Zou, Xiaoyu Shi, Yawen Luo, Ziang Li, Qinghe Wang, Mengfei Li, Chengfeng Zhao, Xintao Wang, Pengfei Wan, Kun Gai, Yuan Liu · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26801 · cited by 0 works (OpenAlex) · open-access PDF
最近在文本到视频生成方面取得的进展使得单片合成具有较高的可靠性,但实际的讲故事创作需要多片视频,具有较强的间拍一致性和细粒控制性。现有的多片视频生成方法几乎具有较强的一致性,但在可控性上仍然短缺。在这篇论文中,我们提出了Mise-en-Video(MeV),一个高度可控的多片视频生成框架,允许视频创作者在3D空间中进行多片拍摄,然后生成相应的多片视频。为了实现这一目标,我们的框架结合了多层次讲述一致性的等级关注机制和3D警惕布局指导,以获得准确的每片空间控制。为了支持培训和评估,我们开发了标准化的注释管道,并构建了一个160K视频
Machine translation (Meta M2M100); the English original follows.
Recent advances in text-to-video generation have enabled high-fidelity single-shot synthesis, yet practical storytelling creation requires multi-shot videos with both strong inter-shot consistency and fine-grained controllability. Existing multi-shot video generation approaches achieve strong consistency but still fall short in controllability. In this paper, we propose Mise-en-Video (MeV), a highly controllable multi-shot video generation framework that allows video creators to conduct staging the multi-shot in the 3D space and then generate the corresponding multi-shot video. To achieve this, our framework combines a hierarchical attention mechanism for multi-level narrative consistency with 3D-aware layout guidance for precise, per-shot spatial control. To support training and evaluation, we develop standardized annotation pipelines and construct a 160K-video dataset with hierarchical multi-shot texts and oriented 3D bounding boxes. Extensive experiments demonstrate that MeV consistently outperforms strong baselines in video quality, inter-shot consistency, and subject-level controllability.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Consistency (knowledge bases), Bounding overwatch, Annotation, Artificial intelligence, Construct (python library)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26801, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange