Four 2026 validation studies on wearables — velocity sensors, EMG timing, a wireless EMG device, and jump tools — agree: reliable for a group or a trend, shakier for one session, muscle, or device comparison.
Three 2026 papers — multi-IMU sync, sweat biosensors, and video-to-force modelling — sit several inferential steps from what they want to measure. The sensor is not the measurement; every modelled step adds error.
Three 2026 studies bolt a task-specific stage onto a general-purpose pose estimator — grading squats, measuring a table-tennis elbow, predicting a fall — and each hits the same wall: the accuracy number belongs to one camera setup.
Two 2026 reviews and two validation studies on markerless kinematics converge on one answer: accuracy is not a single number — it is specific to the joint, the plane, and the task.
The Avatar Talk capstone: body, face, fingers and wrists driving one VRM from a single webcam, all in the browser. Why an arm solve can’t roll the wrist, the thumb bending about the wrong axis, caching frames and counting drops, the neutral face where 0.3 is the new zero, the mirror rule — and an honest ~9 fps, not the 30 I’d claimed.
The Avatar Talk finale: pose, face and hands driving one VRM in a single browser render loop. The One Euro filter that beats the jitter-vs-lag trade, filtering landmarks at the source, MediaPipe’s 52 ARKit blendshapes mapped to VRM expressions, and finger bend-not-splay hand tracking.
Same recipe — detect a pose, track it, classify it — but very different evidence. One 2026 paper grades a physical-therapy exercise against expert ground truth (RTMPose + GRU, ~96%); the other profiles a basketball move with no ground-truth labels, and honestly says so. What validates a pose pipeline isn’t the detector — it’s the ground truth.
You captured the motion — you’re not done. Two July 2026 papers trace the path from validated kinematics to a modeled injury number: an OpenCap markerless scoping review (51 studies), and a badminton-lunge ACL-load model (OpenSim + XGBoost, R² ≈ 0.91). Each inferential layer adds its own uncertainty.
Part 3 of Avatar Talk: retarget MediaPipe pose landmarks onto a VRM avatar’s bone rotations, in the browser. Positions vs rotations, the MediaPipe→VRM coordinate flip and mirror, rest→target quaternions, world→local chains, frame-rate-independent easing, and the single-camera depth fix.
Part 2 of Avatar Talk: load a real 3D VRM avatar in the browser with three.js and @pixiv/three-vrm. Why VRM’s standardized bone map matters, the loading cleanup that counts on a 15 MB model, two-line breathing, and the expression system for lip sync.