Photogrammetry is a capture technique that reconstructs a 3D model from a set of overlapping photographs taken from different angles. Software analyzes shared points across the images to estimate geometry and surface texture, producing a mesh or point cloud of a real-world object or scene.
It is one of the most common ways to create 3D assets from physical reality, alongside newer methods like Gaussian splatting and neural radiance fields. The captured result is typically optimized and converted into a streamable format for delivery.
Point cloud — A common photogrammetry output.
Gaussian splatting — A newer photo-based capture method.
Neural radiance fields (NeRFs) — A neural alternative for reconstructing scenes from photos.
Streaming video reshaped media consumption; we're doing the same for 3D. Join a small team solving tough spatial streaming, content delivery, and developer experience challenges.
Technical deep-dives on adaptive spatial streaming, the infrastructure challenges of 3D at scale, and what we're learning as we build. Written by the team doing the work.
