ai.hackcv
论文精选 60arXiv

PanoWorld: Real-World Panoramic Generation

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/.

AI 解读论文

提出PanoWorld模型,利用全景图的旋转等变性优化长期记忆和物理一致性。

核心方法
利用全景图的旋转等变性,通过固定航向简化摄像机轨迹;引入Dense Panoramic Ray-Conditioning (DPRC) 和 Geometry-aware Memory Augmentation (GMA),结合三阶段训练管道优化模型。
适合谁读
计算机视觉研究者、全景图生成工程师、自动驾驶和虚拟现实产品团队
要解决的问题
全景世界模型中的长期记忆难题,以及现有数据集无法充分评估大规模空间变化和不同光照条件下的物理一致性。
关键实验
在World360数据集上进行了大量实验,证明了PanoWorld的有效性,大幅优于其他方法。
主要贡献
提出了PanoWorld模型,构建了大规模数据集World360,显著提升了物理一致性和模型性能。
意义与局限
PanoWorld在处理大规模空间变化和多样化光照条件方面表现出色,有助于推进全景世界模型的应用。然而,模型的复杂性和计算成本可能限制其在资源受限环境中的部署。
领域:cs.CV作者:Haoyuan Li、Dizhe Zhang、Yuemei Zhou
相关推荐
论文精选 60已解读

Principia: Relational Physics Tests for Video Models· Principia:视频模型的物理测试

Evaluating physical reasoning in video models is difficult because absolute motion measure…

领域:cs.CV作者:Varun Varma Thozhiyoor、Shivam Tripathi、Venkatesh Babu Radhakrishnan
📎 arXiv🕒 09-04 01:59🔗 arxiv.org

本站内容由 LLM 精选聚合,原文版权归 arXiv 所有 · 摘录仅供参考