A metric 3D skeleton from one iPhone. No markers, no suit, no lab.
For thirty years the answer to "how does this body move" was an optical lab: a dozen cameras on a truss, a suit of reflective markers, an afternoon of calibration and a technician to clean the data. It works. It also costs more than a car, never leaves the building, and cannot be pointed at a batter in a cage or a patient in a hallway.
Annual growth of markerless capture through 2030, well ahead of the whole market.
What an optical lab costs, from an entry rig to an in-stadium install.
Joint-angle error two iPhones reach against a marker lab. Multi-camera markerless averages 2.3° in gait.
Hours of cleanup per hour of optical capture. Calibration alone runs one to two hours.
Three capture modes on one screen: a live 3D preview, high-speed capture at 30, 60, 120 or 240 fps, and Track, which records the camera's own motion so a handheld shot can be stabilized later. A wrist remote starts and stops the take from the batter's box.
Every take opens with 1.2 seconds of depth. From it Arikex solves bone lengths, stature, distance and a floor plane, then rejects anything that is not a body, like the ghost a mirror returns. High-speed frames inherit the scale: physics does not care about frame rate.
A 26-keypoint model runs on the phone's neural engine, then a whole-take optimizer lifts it into meters: bone-length constancy, a rigid torso, temporal smoothness, ground contact, with LiDAR arbitrating the folds a single camera cannot see. Two phones triangulate instead.
Joint angles, hip-shoulder separation, trunk lean and their velocities, timed to the frame. A Deep Analysis pass hands only those numbers to a language model and returns a report where every timestamp scrubs the footage. Video never leaves the phone.
Every take is a folder of plain files: video, depth, keypoints, calibration, camera track. The same analysis core runs on the phone and on current-generation Apple silicon, so a phone can do everything alone or just shoot and send. When a session needs a dynamic Gaussian splat, the workstation hands one command to a CUDA box and brings the frames back.
The capture core is the same everywhere: a metric, anatomy-first skeleton with per-segment poses, velocities and confidence. What changes is what you do with it.
Hip-shoulder separation, trunk lean, elbow and knee angles and their angular velocities, timed to the frame at 240 fps. A Deep Analysis pass turns the numbers into cues a coach would give, with every timestamp scrubbing the footage. In-stadium systems do this for $500,000 and a camera crew. A cage needs a tripod.
A metric skeleton with a real floor gives knee and hip flexion through the gait cycle, stride length in centimeters, cadence and left-right asymmetry, from one phone on a stand. Two phones at front and 45° triangulate for the numbers a clinic can act on. Video stays on the device.
Every solved take exports BVH: a pelvis-rooted hierarchy with calibrated bone offsets, root translation and per-joint rotations, plus USDZ of the posed rig. Drop it on any standard humanoid rig in your engine or DCC. Fingers come from the hand model, feet carry real sole orientation.
Stage places a take on a LiDAR-scaled floor with gray props and a camera with a real focal length, then renders a gray-box pass at 24 fps with depth, matte and camera JSON. Sent to a current video generation model, the same framing and the same move come back photoreal. Real faces are never uploaded, the mannequin is.
Track mode records the camera's own path with the performance, so a handheld take becomes both an actor and a camera move. Stabilize it to lock the actor to the floor, or import the move as the Stage camera. Export USDZ, BVH and per-frame camera JSON to your DCC, or skip it entirely.
A single camera cannot tell which way a limb folds in depth. Arikex does not pretend otherwise: LiDAR arbitrates the folds it can measure, the solver enforces what a body can do, and every report carries the take's own self-check, reconstructed stature against the LiDAR measurement. The path to lab-grade numbers is a second phone, and the workstation already walks it.
| Method | Cameras | Joint-angle error |
|---|---|---|
| Optical markers (Vicon, OptiTrack) | 8 to 40 | ~1 mm position |
| Markerless multi-camera, gait meta-analysis | 8+ | 2.3° mean |
| Theia3D, 16 validation studies | 8+ | < 6° RMSE |
| Two iPhones (OpenCap, marker-validated) | 2 | 4.5° MAE |
| One iPhone (OpenCap Monocular, 2026) | 1 | 4.8° MAE |
| Inertial suit (Xsens) | 0 | 6 to 18° RMSE |
| Arikex, one phone with LiDAR scale | 1 | validation shoot planned |
| Arikex, two phones front + 45° | 2 | OpenCap-class pipeline |
Markerless motion capture measures how a body moves from ordinary video, with no reflective markers, no suit and no instrumented room. A neural pose model finds the joints in every frame and a solver lifts them into a real skeleton measured in metres.
Three stages. The camera records; a pose model locates the body's keypoints in each frame; then a whole-take solver turns those flat keypoints into metric 3D using bone-length constancy, a rigid torso, temporal smoothness and ground contact. Arikex adds a LiDAR pre-roll so the skeleton is scaled to the real subject rather than an average one.
Yes. There is nothing to wear and nothing to stick on the athlete or patient. The subject is captured in whatever they already have on, which is why it works in a batting cage, a clinic hallway or on a field rather than only in a laboratory.
Yes. Arikex records at up to 240 frames a second and opens every take with a 1.2 second LiDAR pre-roll that measures the subject's actual bone lengths, stature and the floor, so the solved skeleton is metric rather than relative. The capture, the solve and the analysis all run on the phone.
Published validation puts multi-camera markerless systems at about 2.3 degrees mean joint-angle error in gait, and two smartphones at 4.5 degrees against a marker-based laboratory. Marker systems remain the reference at roughly a millimetre of position. Arikex will publish its own figures after a marker-lab shoot rather than before one.
A marker system tracks reflective balls fixed to the skin with a ring of calibrated cameras, which is the most precise method and the least portable. Markerless infers the same joints from the image itself, so it costs less, sets up in minutes instead of hours, and goes where the movement actually happens, at the price of a few degrees of accuracy.
An optical laboratory runs from roughly twenty five thousand dollars for an entry rig to half a million for an in-stadium install, before calibration time and the technician who cleans the data. Markerless capture on phones a facility already owns removes most of that.
One is enough for joint angles, angular velocities and a coaching read. A second phone, placed in front and 45 degrees to the side, triangulates a true 3D skeleton and removes the depth ambiguity a single camera cannot resolve. Up to four are supported.
Yes. Every solved take exports BVH and USDZ: a pelvis-rooted hierarchy with calibrated bone offsets, root translation and per-joint rotations that retargets onto any standard humanoid rig. No licensed body model is involved, so the motion is yours to use.
Arikex is in private testing with athletes, coaches and clinicians now. If you run a facility, a clinic, a studio or a pipeline that needs motion, we want to point it at yours.
Request a capture session