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
Kemajuan baru-baru ini dalam generasi teks-ke-video telah memungkinkan sintesis single-shot fidelitas tinggi, namun kreasi narasi praktis membutuhkan video multi-shot dengan konsistensi inter-shot yang kuat dan kontrol halus. Pendekatan generasi video multi-shot yang ada hampir konsistensi yang kuat tetapi masih kekurangan dalam kontrol. Dalam makalah ini, kami mengusulkan Mise-en-Video (MeV), kerangka kerja generasi video multi-shot yang sangat terkendali yang memungkinkan pembuat video untuk melakukan pemutaran multi-shot di ruang 3D dan kemudian menghasilkan video multi-shot yang sesuai. Untuk mencapai ini, kerangka kerja kami menggabungkan mekanisme perhatian hierarkis untuk konsistensi narasi multi-level dengan panduan tata letak 3D-aware untuk kontrol spasial yang akurat, per-shot. Untuk mendukung pelatihan dan evaluasi, kami mengembangkan
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