Robust Video Matting vs VCam

Robust Video Matting is a free project for separating people from video backgrounds. It processes frames with a recurrent neural network that carries temporal memory, and the project says it can perform matting in real time without additional inputs. A browser webcam demo runs the model live and can visualize its recurrent states. The conversion API accepts a video or image sequence and can produce a composited video or PNG sequence, optionally including alpha and foreground outputs.

Models are available for PyTorch, TorchHub, TorchScript, ONNX, TensorFlow, TensorFlow.js, and CoreML. MobileNetv3 is recommended for most uses; ResNet50 is larger and described as offering small performance improvements. The README reports GPU throughput figures, including 4K at 76 FPS and HD at 104 FPS on a GTX 1080 Ti, and 4K at 154 FPS and HD at 172 FPS on an RTX 3090 with FP16 under specified settings. The project cautions that file conversion runs much slower because its script does not use hardware video encoding or decoding or parallel tensor transfers. CoreML models require iOS 13 or later and do not support dynamic resolution. The code is GPL-3.0 licensed.

VCam is a locally powered AI meeting companion for changing webcam backgrounds and enhancing camera video. It can remove, replace, or blur backgrounds, with more than 1,000 virtual backgrounds and options to use an uploaded image, video, or Unsplash stock photo. AI auto-framing follows the user's face, while studio lighting effects brighten the feed. Pause Loop repeats the camera feed during a break so the user can return without disturbing the meeting. Nametags show a name and job title; four designs are listed, with customization described as coming soon. VCam lists compatibility with Google Meet, Microsoft Teams, Zoom, Discord, OBS Studio, and specialized software such as NCR's TellerNow, and its virtual camera can be used across multiple platforms at once. VCam says processing runs on the user's device and camera-feed data is not sent to its servers. Starter is free, but includes a watermark and up to 500MB storage. Personal costs $48 a year; Business costs $72 a year per user. Recommended systems are Windows 10 or higher and macOS Ventura 13.1 or higher.