将世界模拟模型扎根于现实世界中的城市
Grounding World Simulation Models in a Real-World Metropolis
AI总结：
本文提出Seoul World Model，通过检索增强的条件生成真实城市场景，解决时间错位和轨迹多样性问题，生成高保真、时序一致的长时景视频。
摘要：
如果一个世界模拟模型能够渲染不是想象中的环境，而是真实存在的城市呢？先前的生成世界模型通过想象所有内容来合成视觉上合理但人工的环境。我们提出了首尔世界模型（SWM），这是一个扎根于实际城市首尔的城市级世界模型。SWM通过检索增强的条件生成来锚定自回归视频生成，利用附近街景图像进行条件生成。然而，这种设计引入了几个挑战，包括检索参考与动态目标场景之间的时间错位、有限的轨迹多样性以及从车辆搭载拍摄中获得的数据稀疏性。我们通过跨时间配对、大规模合成数据集实现多样化的摄像轨迹，以及视图插值流程从稀疏街景图像中合成连贯的训练视频来解决这些问题。我们进一步引入虚拟前瞻Sink以稳定长周期生成，通过持续将每个片段重新锚定到未来位置的检索图像来实现。我们对SWM在三个城市：首尔、釜山和安阿伯进行了评估。SWM在生成空间上忠实、时间上一致、长周期视频方面优于现有方法，这些视频基于实际城市环境中的轨迹，可达数百米，同时支持多样的摄像运动和文本提示的场景变化。
英文摘要：
What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existing methods in generating spatially faithful, temporally consistent, long-horizon videos grounded in actual urban environments over trajectories reaching hundreds of meters, while supporting diverse camera movements and text-prompted scenario variations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
