Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Joey Tianyi Zhou, Chi Zhang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31640 · open-access PDF
视频传播模型已经学习了丰富的3D/4D预先,使其对场景生成和视频重现有前景。然而,它们在空间任务中的使用受到不准确的摄像头控制,空间和时间的不一致以及与场景动态混合的摄像头运动的限制。现有的方法,如任务特定的精细调节和过程后扭曲,经常引入视觉文物,一般化不良,或承担高计算成本。我们建议WorldForge V2实现准确的摄像头控制,同时保持预训练视频模型的生成能力。
Machine translation (Meta M2M100); the English original follows.
Video diffusion models have learned rich 3D/4D priors, making them promising for scene generation and video re-rendering. However, their use in spatial tasks is limited by imprecise camera control, spatial and temporal inconsistencies, and entangled camera motion with scene dynamics. Existing approaches, such as task-specific fine-tuning and post-process warping, often introduce visual artifacts, generalize poorly, or incur high computational costs. We propose WorldForge V2 to achieve accurate camera control while preserving the generative capabilities of pretrained video models. We first deve
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31640, 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