360∘ videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees. To achieve more user-friendly and personalized content creation in 360∘ video format, we seek to lift standard perspective videos into 360∘ equirectangular videos. To this end, we introduce Imagine360, the first perspective-to-360∘ video generation framework that creates high-quality 360∘ videos with rich and diverse motion patterns from video anchors. Imagine360 learns fine-grained spherical visual and motion patterns from limited 360∘ video data with several key designs. 1) Firstly we adopt the dual-branch design, including a perspective and a panorama video denoising branch to provide local and global constraints for 360∘ video generation, with motion module and spatial LoRA layers fine-tuned on extended web 360∘ videos. 2) Additionally, an antipodal mask is devised to capture long-range motion dependencies, enhancing the reversed camera motion between antipodal pixels across hemispheres. 3) To handle diverse perspective video inputs, we propose elevation-aware designs that adapt to varying video masking due to changing elevations across frames. Extensive experiments show Imagine360 achieves superior graphics quality and motion coherence among state-of-the-art 360∘ video generation methods. We believe Imagine360 holds promise for advancing personalized, immersive 360∘ video creation.
Cite
@article{arxiv.2412.03552,
title = {Imagine360: Immersive 360 Video Generation from Perspective Anchor},
author = {Jing Tan and Shuai Yang and Tong Wu and Jingwen He and Yuwei Guo and Ziwei Liu and Dahua Lin},
journal= {arXiv preprint arXiv:2412.03552},
year = {2024}
}