PanoWorld: Real-World Panoramic Generation
Haoyuan Li Dizhe Zhang Yuemei Zhou Xiangkai Zhang Haoran Feng Xiaofan Lin Wenjie Jiang Bo Du Ming-Hsuan Yang Lu Qi
作者信息
Abstract
In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, where rotation can be treated as an implicit geometric transformation.Building on this insight, we propose PanoWorld, which simplifies camera trajectories into translations via fixed headings for both current-action modeling and long-range memory through Dense Panoramic Ray-Conditioning (DPRC) and Geometry-aware Memory Augmentation (GMA).Then, a three-stage training pipeline is introduced to progressively optimize each component. To better evaluate physical consistency under large-scale spatial variations and diverse illumination conditions, where existing datasets are relatively stable, we construct World360, a large-scale dataset consisting of both real-world video clips collected via panoramic unmanned aerial vehicles and high-quality simulated clips generated by AirSim360.Extensive experiments on World360 demonstrate the effectiveness of PanoWorld, outperforming alternative methods by a large margin.Our models, training code, and dataset will be publicly available. More information can be found on our project page: https://lihaoy-ux.github.io/panoworld-page/.引用本文复制引用
Haoyuan Li,Dizhe Zhang,Yuemei Zhou,Xiangkai Zhang,Haoran Feng,Xiaofan Lin,Wenjie Jiang,Bo Du,Ming-Hsuan Yang,Lu Qi.PanoWorld: Real-World Panoramic Generation[EB/OL].(2026-07-10)[2026-07-14].https://arxiv.org/abs/2607.09661.学科分类
计算技术、计算机技术
|国家预印本平台