WildCity：一個真實世界城市規模的渲染、模擬與空間智能測試平台。

摘要

人類能夠在陌生的城市中導航，並逐步形成涵蓋數十平方公里、連貫的空間心智地圖。人工智慧是否能建構同等規模的空間表徵？儘管近期基礎模型在場景重建與具身智能方面取得了進展，但要擴展至整個城市仍是一項開創性的挑戰，主因在於缺乏城市規模的數據。為填補這一差距，我們引入了WildCity——一個由自動駕駛車隊在複雜城市環境中行駛所收集的真實世界多模態數據集。該數據集包含18條軌跡，每條平均長度為83.7公里，並保留了野外感知的核心挑戰，例如動態物體、光照變化及不完美的相機姿態。我們進一步建立了一個專為城市環境量身訂製的重建基準，並將重建後的環境轉化為封閉迴路模擬器。除了數據集與基準之外，我們系統性地分析了邁向可模擬的城市數位孿生之路上的關鍵挑戰：可擴展性、外推能力及不確定性。最終，WildCity旨在不僅推動城市規模的渲染進展，更廣泛地促進人工智慧在與人類認知規模相當的空間中，能夠感知、記憶與推理的能力。專案頁面：https://han-xiangyu.github.io/Wild-City/

English

Humans can navigate an unfamiliar city and gradually form a coherent spatial mental map spanning tens of square kilometers. Can AI build spatial representations at a comparable scale? Although recent foundation models have advanced scene reconstruction and embodied intelligence, scaling to entire cities remains an open challenge, primarily due to the lack of city-scale data. To bridge the gap, we introduce WildCity, a real-world multimodal dataset collected by autonomous fleets traversing complex urban environments. Our dataset includes 18 trajectories, each averaging 83.7 kilometers in length, and preserves the core challenges of in-the-wild perception, e.g., dynamic objects, lighting variations, and imperfect camera poses. We further establish an urban-tailored reconstruction baseline and convert the reconstructed environments into a closed-loop simulator. Beyond the dataset and baseline, we systematically analyze the key challenges on the path to simulation-ready urban digital twins: scalability, extrapolation, and uncertainty. Ultimately, WildCity aims to catalyze progress not only in city-scale rendering, but more broadly in the pursuit of AI that can perceive, remember, and reason across space at a scale comparable to human cognition. Project page: https://han-xiangyu.github.io/Wild-City/