A 128,892-clip, 2,826-hour real-world video dataset with camera trajectories, temporally grounded captions, and 982 revisit-rich panoramic sequences for interactive world-model training.
PanoWorld: Real-World Panoramic Generation
1 Pith paper cite this work. Polarity classification is still indexing.
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/.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Sekai2: From World Exploration to Interactive World Modeling
A 128,892-clip, 2,826-hour real-world video dataset with camera trajectories, temporally grounded captions, and 982 revisit-rich panoramic sequences for interactive world-model training.