Applied computer vision, grounded in method
CivicSet develops its two products around well-understood methods: sub-pixel alignment and fusion for super-resolution, and Procrustes geometry for facial verification.
Research focus areas
Sub-pixel alignment
Cross-correlation shift estimation for burst-frame super-resolution.
Robust fusion
Shift-and-add fusion that suppresses noise and recovers detail.
Procrustes geometry
Closed-form translation, scale, and rotation alignment of facial landmarks.
Verification metrics
Similarity and distance scoring for 1:1 face comparison.
Explainability
Metrics that make each result auditable rather than opaque.
In-process compute
Delivering computer vision without a separate service plane.
Research collaboration
We welcome collaboration with researchers and teams exploring super-resolution and facial verification methods.
Two products,
in the works
Multi-Frame Super-Resolution and Facial Verification are in active development. Leave your email and be first to know when they launch.