Articles, notes, and
field reports.
Technical deep dives, lessons from the field, and the thinking behind how we build spatial intelligence.
Why Metric 3D Matters More Than Pretty Point Clouds
Most 3D reconstruction tools optimize for visual fidelity. We optimize for geometric accuracy — and the difference changes what you can actually do with the data.
From Earthquake Rubble to Queryable Structure in 4 Minutes
A field report from the 2023 Turkey earthquake response, where we first tested real-time 3D reconstruction for rescue coordination.
Scene Graphs vs. Neural Radiance: What Engineers Actually Need
NeRFs generate beautiful renders. Scene graphs generate actionable intelligence. Here's why the distinction matters for real-world applications.
Building Digital Twins at City Scale
City-scale 3D reconstruction introduces unique challenges around data fusion, coordinate systems, and persistent accuracy over time.
Real-time Fire Simulation on Actual Terrain Data
How we moved fire spread prediction from synthetic terrain to actual reconstructed environments — and why it changes everything for first responders.
The API-First Approach to Spatial Intelligence
Why we built Percept as an API first and a platform second — and how it enables an ecosystem of spatial AI applications.