WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-07-07 with 13 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Xiangyu Han et al. |
| Year | 2026 |
| HF Upvotes | 13 |
| arXiv | 2607.06838 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
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/
Engineering Breakdown
The Problem
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. 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.
The Approach
To bridge the gap, we introduce WildCity, a real-world multimodal dataset collected by autonomous fleets traversing complex urban environments.
Key Results
Project page: https://han-xiangyu.github.io/Wild-City/
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Realworld
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::