# Rock-100/FaceKit

[CVPR 2018] Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

Repository: https://github.com/Rock-100/FaceKit
Canonical: https://ross.abutalabs.com/products/facekit
Language: C++
License: NOASSERTION
License Family: other
Topics: face-detection
Last push: 2023-05-11T12:29:37+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3060, "days_push": 1210, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1083, forks 293 (observed 2026-08-28T04:03:31.093062+00:00)

## What it is
FaceKit is a C++ toolkit implementing Progressive Calibration Networks (PCN) for real-time rotation-invariant face detection and tracking, presented at CVPR 2018. It also includes utilities for face warping, skin smoothing, and face color transfer.

## Use cases
- detect faces in images with arbitrary rotation in real time
- track faces across video frames
- warp rotated faces to upright orientation
- smooth skin in face photos
- transfer color between face images

## When to choose
- you need fast, rotation-invariant face detection in a C++ pipeline
- you want face tracking plus post-processing like warping or smoothing in one toolkit

## When to avoid
- you need a maintained general-purpose face detection stack with modern model support
- you require a permissive license for commercial use without review (license is non-standard)
- you prefer Python-based tooling

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, image-processing, deep-learning
- platform: cpp, cross-platform
- tags: face-detection, rotation-invariant, face-tracking, face-warping, skin-smoothing, color-transfer, cvpr-2018

## Member repositories
- Rock-100/FaceKit (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.093062+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:50:20.584659+00:00, confidence not recorded.
  - readme: https://github.com/Rock-100/FaceKit (fetched 2026-08-28T04:03:31.093062+00:00, sha 4bc6a41e25f6)
- Data as of 2026-08-30T08:39:29.467469+00:00.