CityRAG: Stepping Into a City via Spatially-Grounded Video Generation

Hugging Face Daily Papers Papers

Summary

CityRAG introduces a video generative model that produces long, physically grounded, 3D-consistent videos of real-world cities using geo-registered data, enabling realistic navigation and simulation for robotics and autonomous driving.

We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video generative models can produce a plausible sequence that is consistent with a text (T2V) or image (I2V) prompt. However, the capability to reconstruct the real world under arbitrary weather conditions and dynamic object configurations is essential for downstream applications including autonomous driving and robotics simulation. To this end, we present CityRAG, a video generative model that leverages large corpora of geo-registered data as context to ground generation to the physical scene, while maintaining learned priors for complex motion and appearance changes. CityRAG relies on temporally unaligned training data, which teaches the model to semantically disentangle the underlying scene from its transient attributes. Our experiments demonstrate that CityRAG can generate coherent minutes-long, physically grounded video sequences, maintain weather and lighting conditions over thousands of frames, achieve loop closure, and navigate complex trajectories to reconstruct real-world geography.
Original Article
View Cached Full Text

Cached at: 04/22/26, 02:41 PM

Paper page - CityRAG: Stepping Into a City via Spatially-Grounded Video Generation

Source: https://huggingface.co/papers/2604.19741

Abstract

CityRAG generates long-term, physically grounded video sequences that maintain environmental consistency and support complex navigation through real-world geography using geo-registered data as context.

We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existingvideo generative modelscan produce a plausible sequence that is consistent with a text (T2V) or image (I2V) prompt. However, the capability to reconstruct the real world under arbitrary weather conditions and dynamic object configurations is essential for downstream applications including autonomous driving and robotics simulation. To this end, we present CityRAG, a video generative model that leverages large corpora ofgeo-registered dataas context to ground generation to the physical scene, while maintaining learned priors for complex motion and appearance changes. CityRAG relies on temporally unaligned training data, which teaches the model to semantically disentangle the underlying scene from its transient attributes. Our experiments demonstrate that CityRAG can generate coherent minutes-long, physically grounded video sequences, maintain weather and lighting conditions over thousands of frames, achieveloop closure, and navigate complex trajectories to reconstruct real-world geography.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2604\.19741

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2604.19741 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2604.19741 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2604.19741 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

Hugging Face Daily Papers

Sat3DGen introduces a geometry-first approach for generating street-level 3D scenes from a single satellite image, achieving improved geometric accuracy and photorealism through novel constraints and training strategies. The method demonstrates significant improvements over prior work on the VIGOR-OOD benchmark.

ABot-Earth 0.5: Generative 3D Earth Model

Hugging Face Daily Papers

ABot-Earth 0.5 is a generative 3D framework that synthesizes realistic 3D urban environments from satellite imagery using 3D Gaussian Splatting, enabling real-time visualization and closed-loop UAV navigation at low cost.

Video generation models as world simulators

OpenAI Blog

OpenAI's technical report on Sora describes a video generation model that unifies diverse visual data through visual patches, enabling large-scale training of generative models capable of producing high-definition videos up to one minute long across variable durations, aspect ratios, and resolutions.