NAME

VirtualCam - Face tracking and background effects for any video call app

SYNOPSIS

2020 - 2026; Python, OpenCV, MediaPipe, Swift, SwiftUI, v4l2loopback
github | product page | demo video

DESCRIPTION

Real-time virtual camera pipeline that captures a camera or screen, runs segmentation and face tracking, and outputs through v4l2loopback on Linux or OBS Virtual Camera on macOS. Started in 2020 because Zoom had no virtual backgrounds on Linux; now adds background blur and swap, desk view, gesture reactions, and a native SwiftUI menu bar app that drives a managed Python worker over a JSONL protocol. 71 GitHub stars.

HIGHLIGHTS

• Bounded frame loop that drains a command queue between frames, with output cadence decoupled from processing speed
• Segmentation backends (MediaPipe, Apple Vision, chroma key, motion-aware mask smoothing) compared on measured fixtures
• Native macOS menu bar app with profiles, camera identity handling, live-applied effects, and hold-to-compare
• Stabilized face-tracking framing with deadzones, time constants, and lost-face handling, plus desk-view perspective correction

MEDIA

SEE ALSO

* projects(7), all projects
* ari(7), the resume
* PDF Resume: Download Resume