Newest papers

Mise-en-Video: Fine-Grained 3D Control for Multi-Shot Video Generation

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

French

Les progrès récents en matière de génération de texte à vidéo ont permis une synthèse de single-shot à haute fiabilité, mais la création pratique d'histoires nécessite des vidéos multi-shot avec à la fois une forte cohérence inter-shot et une maîtrise à grains fins. Les approches de génération de vidéo multi-shot existantes offrent une cohérence particulièrement forte, mais ne manquent toujours pas de contrôle. Dans ce document, nous proposons Mise-en-Video (MeV), un cadre de génération de vidéo multi-shot hautement contrôlable qui permet aux créateurs de vidéo de réaliser la mise en scène du multi-shot dans l'espace 3D, puis de générer la vidéo multi-shot correspondante. Pour ce faire, notre cadre combine un mécanisme d'attention hiérarchique pour la

Machine translation (Meta M2M100); the English original follows.

Abstract

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)

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange