You-Zhe Xie, Ting-Wei Chou, Yu-Hsuan Li, Kaipeng Zhang, Zhixiang Wang, Yu-Lun Liu
OuroWorld is a framework that turns static 3D scenes into dynamic 3D cinemagraphs with diverse motion. It uses a vision-language model and video synthesis to create looping videos. OuroWorld outperforms baselines in user-study comparisons.
OuroWorld enables the creation of immersive and interactive 3D environments, which can be applied to various fields such as gaming, film, and architecture. This technology has the potential to revolutionize the way we experience and interact with 3D worlds. It can also be used to generate realistic training data for AI models.
Thank you to arXiv for use of its open access interoperability. arxiv.org. aibrief.ai is not affiliated with or endorsed by arXiv.