ai engine
AI Engine
Ensemble models estimate body landmarks and volumetric shape from multi-view imagery. Outputs include uncertainty bands—not single false-precision numbers.
Technology
Built for trust and repeatability
Our stack balances on-device guidance with cloud reconstruction—always with uncertainty bands, never false precision.
computer vision
Computer Vision
Pose estimation and silhouette extraction stabilize framing so weekly scans remain comparable.
body mapping
Body Mapping
A parametric mesh is fit to observed contours, then refined for circumference extraction along anatomical planes.
privacy
Privacy & Security
TLS in transit, storage protected by our cloud infrastructure provider, role-based access for family and trainer shares. We do not sell personal scan data.
accuracy
Accuracy methodology
In simulated testing across diverse body models, key circumferences typically fall within roughly ±0.5–1 cm on average (some measurements up to ~3–4 cm in worst cases). Real-world validation against physical tape measures is ongoing. Results vary with clothing, lighting, and pose. Forma is not a medical diagnostic device.
ml
Machine Learning
Models are validated on diverse body shapes. We continuously evaluate bias and publish methodology notes for enterprise customers.
cloud
Cloud processing
Heavy reconstruction jobs run in regional cloud workers for speed; you can request deletion of cloud copies anytime.
edge
Edge processing
Pose guidance and preview run on-device so you get real-time feedback before upload.
encryption
Data encryption
Modern TLS for APIs and uploads; stored artifacts are protected by our cloud infrastructure provider's storage security. Access logs available for business accounts.