OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
This addresses the issue of incomplete and inconsistent scene modeling in video generation for applications like virtual reality or simulation, though it appears incremental as it builds on existing panoramic and video generation techniques.
The authors tackled the problem of limited scene coverage and consistency in video generation by proposing OmniRoam, a panoramic video generation framework that enables long-horizon scene wandering, resulting in improved visual quality, controllability, and long-term consistency compared to state-of-the-art methods.
Modeling scenes using video generation models has garnered growing research interest in recent years. However, most existing approaches rely on perspective video models that synthesize only limited observations of a scene, leading to issues of completeness and global consistency. We propose OmniRoam, a controllable panoramic video generation framework that exploits the rich per-frame scene coverage and inherent long-term spatial and temporal consistency of panoramic representation, enabling long-horizon scene wandering. Our framework begins with a preview stage, where a trajectory-controlled video generation model creates a quick overview of the scene from a given input image or video. Then, in the refine stage, this video is temporally extended and spatially upsampled to produce long-range, high-resolution videos, thus enabling high-fidelity world wandering. To train our model, we introduce two panoramic video datasets that incorporate both synthetic and real-world captured videos. Experiments show that our framework consistently outperforms state-of-the-art methods in terms of visual quality, controllability, and long-term scene consistency, both qualitatively and quantitatively. We further showcase several extensions of this framework, including real-time video generation and 3D reconstruction. Code is available at https://github.com/yuhengliu02/OmniRoam.