05

CAPTURE / 05 — 4D CAPTURE

4D Capture

Volumetric performance capture for virtual production and real-time pipelines — temporally consistent 4D scan sequences and volumetric assets built for ICVFX and interactive, geometry that changes frame by frame.

[ REAL-TIME READY / ICVFX PIPELINES ]

4D facial performance solve — screaming expression reconstructed as untextured geometry

SRC / 4D SOLVE / PER-FRAME GEOMETRY

WHAT IT IS

Capture that moves through time.

A traditional scan freezes a single instant. 4D capture records a performance as a sequence of scans — geometry that changes frame by frame — so a facial expression, a piece of cloth, or a full body in motion can be reconstructed as it actually moved, not approximated with rigs and simulation.

It takes a synchronized array, a pipeline that keeps geometry stable from frame to frame, and crews who understand how the result has to behave inside a real-time engine — not just look good in a turntable. When you need a photoreal, walk-through radiance field of a set or object rather than a moving performance, that’s 3D Gaussian Splatting — a separate service with its own page.

Talent performing inside the synchronized volumetric camera array
01 The array, mid-performance
A single solved 4D frame — facial geometry reconstructed from that instant of the take
02 One solved frame of the sequence

HOW SCANABLE DOES IT

Volumetric capture, engine-ready delivery.

We capture performance sequences on the C.A.L.V.I.N.N.™ array and process them into temporally consistent 4D data, then deliver in the form your pipeline needs: per-frame geometry or volumetric sequences tuned for real-time playback. Everything runs through our color-calibrated RAW pipeline, so the look holds up whether it lands in an offline render or on an LED volume.

Because C.A.L.V.I.N.N.™ is modular and built to travel on its own, we can capture 4D sequences on your production instead of confining them to a fixed stage — mobilized from six cities to wherever the performance happens.

[ 4D SEQUENCES / PER-FRAME GEOMETRY / VOLUMETRIC / REAL-TIME PLAYBACK ]

A single frame of a performance seen from every camera in the C.A.L.V.I.N.N. array at once — the multi-view data a 4D solve is built from FIG.05 / ONE FRAME, EVERY ANGLE

WHAT YOU RECEIVE

Assets that run in real time.

  • 4D scan sequencesTemporally consistent per-frame geometry of a performance.
  • 4D Gaussian splat sequencesMoving subjects as real-time splats, engine-ready.
  • Volumetric assetsReal-time volumes for ICVFX and interactive pipelines.
  • Pipeline handoffDelivered to the specs your real-time engine expects.

START HERE

Bring performance capture into real time.

Tell us the shot and the engine it has to run in. We’ll scope the 4D or splat capture around it.

Request a Quote

FAQ

Common questions

What is the difference between 3D scanning and 4D capture?

A 3D scan is a single instant — one frame of geometry and texture. 4D capture is performance over time: the same volumetric capture repeated across a sequence, so motion and deformation are captured, not simulated after the fact.

What is C.A.L.V.I.N.N.™?

A separate modular array built in house for volumetric and machine-learning capture, including 4D Gaussian splatting. It is a distinct system from the Mobile CyberSCAN™ Studios, which handle static scanning and OLAT.

Does genlock actually matter for Gaussian splatting?

Yes. If the cameras are not genlocked, each one is sampling a slightly different moment, and any reconstruction of a moving subject inherits that error. Every array we build is genlocked for that reason.

How long do you need on set before you can shoot?

About 15 minutes from arrival to capture-ready — on a stage, on location, or in a parking lot. The studio travels to production, not the other way around.