BGRemove.video vs Robust Video Matting

BGRemove.video is a free web service that removes video backgrounds and exports transparent clips with an alpha channel. It accepts MP4, MOV, WebM, M4V, and GIF uploads up to 60 seconds and 2 GB. Its AI follows subjects across frames to reduce flicker and keep edges stable during movement. Transparent output is WebM using VP9 alpha, with the source dimensions preserved. You can place a solid color, blur, image, or video behind a processed clip and export an MP4 without consuming another removal allowance. The free plan costs nothing and allows three successful removals per 24-hour window, with no watermark. Files are processed in the EU and retained for 24 hours, or deleted sooner when requested. Google is the only sign-in option. The maker says uploads are not used to train its models or its provider’s models. Manual edge refinement is unavailable, and glass, smoke, fine mesh, depth-swapping overlaps, and severely underexposed footage are difficult cases.

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.