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
पाठ-विडियो उत्पादन में हाल के प्रगतियां उच्च भरोसेमंदता एकल शॉट संश्लेषण की अनुमति देती हैं, फिर भी व्यावहारिक कहानियों के निर्माण में मजबूत इंटर-शॉट अनुरूपता और अच्छी तरह से नियंत्रित किया जा सकता दोनों के साथ बहु-शॉट वीडियो की आवश्यकता होती है। मौजूदा बहु-शॉट वीडियो उत्पादन दृष्टिकोण लगभग मजबूत अनुरूपता है, लेकिन नियंत्रण में अभी भी कम हैं। इस दस्तावेज़ में, हम Mise-en-Video (MeV) का प्रस्ताव करते हैं, एक अत्यधिक नियंत्रित बहु-शॉट वीडियो उत्पादन फ्रेमवर्क जो वीडियो निर्माताओं को 3 डी स्थान में बहु-शॉट को स्टेज करने की अनुमति देता है और फिर अनुरूप बहु-शॉट वीडियो उत्
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