Robust Video Matting vs VideoBGNinja

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.

VideoBGNinja is a web tool for removing backgrounds from short videos of people without a green screen or account. Its AI matting separates the person frame by frame and follows that subject through the clip. You can upload MP4, MOV, WebM, MKV, AVI, M4V, MPG, MPEG, WMV, or 3GP files. Outputs include transparent WebM, transparent GIF, green-screen MP4, and alpha-matte MP4; paid passes also provide ProRes 4444 MOV with alpha. The free plan costs nothing and handles clips up to 90 seconds, 2 GB, and 1920 px on the longest side. A free e-mail pass offers four minutes, 4 GB, and 2560 px. Paid passes cost €3 as a one-time purchase for 24 hours or €5, paid once for 30 days, raising limits to four minutes, 4 GB, and 3840 px. Processing runs in the Netherlands, with uploads deleted after processing.