A point cloud is a 3D representation made of many individual points in space, each with a position and often a color, that together describe the surface or volume of an object or scene. Point clouds are commonly produced by LiDAR scanners, depth sensors, and photogrammetry.
They serve as an intermediate capture format that can be meshed, optimized, or used directly in point-based rendering. Gaussian splatting extends the idea by giving each point shape and view-dependent appearance.
Photogrammetry — A common way point clouds are created.
Gaussian splatting — An extension of the point-based idea.
Level of detail (LOD) — How dense point data is simplified for delivery.
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.
