Volumetric video captures a moving subject or scene in three dimensions over time, producing a sequence of 3D frames that can be viewed from any angle — not just the single fixed camera of traditional video.
It is typically captured with arrays of cameras or depth sensors and reconstructed into per-frame meshes or point-based representations. Because each frame is full 3D, volumetric video suits AR, VR, and free-viewpoint playback, but it produces large amounts of data that must be optimized and streamed.
Point cloud — A common per-frame representation for volumetric capture.
3D streaming — How heavy volumetric data reaches viewers.
Photogrammetry — A related approach to reconstructing reality in 3D.
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.
