OVER logo

Open Science for Spatial Intelligence and Physical AI

We publish our work in the open — papers, datasets and models built on the world's largest 3D map. Our research spans Large Geospatial Models, machine perception and spatial intelligence, bridging real-world 3D data and the AI systems that will act in the physical world.
Research NoteLGMMachine PerceptionFine-Tuning

Can 1,000 Open Scenes Make a State-of-the-Art 3D Model Better?

Assessing the OVER Dataset by Fine-Tuning a 3D Foundation Model on Its Open Sample

OVER Research

An empirical assessment of the OVER dataset for research, run entirely on OverMaps-1k — the open 1,000-scene sample anyone can download from Hugging Face: pose accuracy improves visibly on our domain, catastrophic forgetting is measured and defused through WiSE weight merging, and a scaling analysis shows how much data the gain requires.

Read the StudyOverMaps-1k
Technical ReportDatasetLGMMachine Perception

The OVER 3D Maps Dataset

Internet-Scale Real-World 3D Data for Training Large Geospatial Models

OVER Research

A technical overview of the OVER 3D Maps Dataset: 270K+ real-world indoor and outdoor locations with 100M+ images, depth maps and metric scaling data — orders of magnitude larger than the datasets powering current Vision Foundation Models, and built for training Large Geospatial Models.

Technical ReportProject Page
Open DatasetDatasetOpen Source

OverMaps-1k

An Open Dataset of 1,000 Real-World 3D Maps

OVER Research

An open-source sample of the OVER 3D Maps Dataset released on Hugging Face: 1,000 real-world 3D maps with multi-view images, depth and metric scale, ready for benchmarking visual relocalization, depth estimation and 3D reconstruction models.

Hugging FaceProject Page
Open Source

Code, models and data

Everything we release lives on GitHub and Hugging Face — follow along, open issues, build with us.

GitHub

OVR-Platform — SDKs, tools and research code.

Hugging Face

OverTheReality — open datasets and model releases.

Built on the OVER 3D Maps Dataset

Our research is grounded in the same dataset that powers the OVER network: hundreds of thousands of real-world 3D maps with images, depth and metric scale. Learn how it enables Large Geospatial Models and machine perception at scale.
Large Geospatial ModelsResearch Collaborations