BackgroundRemover vs Robust Video Matting
BackgroundRemover
github.comRobust Video Matting
github.comSide by side
| Figure | BackgroundRemover | Robust Video Matting |
|---|---|---|
| Price from | $9/mo | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | Yes | — |
| Web | Yes | Yes |
| Windows | Yes | — |
| macOS | Yes | — |
| Linux | Yes | Yes |
| iOS | — | Yes |
| Android | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 6 | 1 |
| Spec score · Video Background Removal Software | 9.4 (#1) | 8.1 (#11) |
| Spec score · AI Video Background Removers | 9.4 (#2) | 8.2 (#13) |
| Model choices | Users can select u2net for general subjects, u2net_human_seg for people or u2netp for faster lighter processing. | The project recommends MobileNetv3 for most use cases and describes ResNet50 as a larger variant with small performance improvements. |
| Purpose | BackgroundRemover uses AI to remove backgrounds from images and videos. | Robust Video Matting is designed for human video matting and uses a recurrent neural network with temporal memory to process video frames. |
Plans
BackgroundRemover
- FreeFree
- API credits$1, paid once
- Pro (monthly)$12 a month
- Pro monthly$12 a month
- Pro (annual)$108 a year
- Pro annual$108 a year
In their own words
BackgroundRemover
BackgroundRemover uses AI to remove image and video backgrounds, with options for people, general subjects, or faster processing. Images can be refined with alpha matting or mask output, then given a color or image background; video output can be transparent MOV, matte key, GIF, or a composite over another image or video. Its command-line formats include JPG, JPEG, PNG, HEIC, and HEIF images, and MP4, MOV, WebM, OGG, and GIF video. The open-source project can be installed locally for free with pip or from source, and it offers a local HTTP API as well as a hosted REST API with examples in Python, PHP, JavaScript, and C#. GPU detection is automatic, with CPU fallback when needed. The Free plan is free and allows one standard-resolution transparent PNG image daily, short videos, and ads, without batch processing. Pro (annual) is $9 a year, billed at US$ 108.0 annually; Pro (monthly) is $12 a month.
Robust Video Matting
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.