RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML
GraphCanon updated 3w · GitHub synced 3w
Decision brief
RobustVideoMatting is a deep-learning-based video matting tool using recurrent neural networks for real-time processing on videos with temporal memory.
Good fit when
- When working with human video matting that requires high frames per second, as it can achieve 4K 76FPS and HD 104FPS on Nvidia GTX 1080 Ti GPU.
- For applications needing real-time processing without the requirement for additional inputs beyond the video itself.
Avoid when
- If you require matting capabilities that do not focus on human-like targets, as RVM is specifically designed with this in mind.
- In scenarios where a model smaller than the MobileNetv3 or ResNet50 options provided by the tool cannot be used due to memory constraints or speed requirements.
- Hosting:
- self hosted
- Pricing:
- freemium - The tool is freely available under GPL-3.0, with no associated costs.
- Requirements:
- A relevant inference framework such as PyTorch or TensorFlow must be installed.; The tool requires a GPU for optimal performance, particularly for handling high-resolution videos.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (849d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install RobustVideoMattingSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Video matting using recurrent neural networks for temporal guidance processing videos in real time.
Capability facts
- Languages
- python
Source: github.language · Jul 31, 2026
Categories
Tags
README
Robust Video Matting (RVM)
English | 中文
Official repository for the paper Robust High-Resolution Video Matting with Temporal Guidance. RVM is specifically designed for robust human video matting. Unlike existing neural models that process frames as independent images, RVM uses a recurrent neural network to process videos with temporal memory. RVM can perform matting in real-time on any videos without additional inputs. It achieves 4K 76FPS and HD 104FPS on an Nvidia GTX 1080 Ti GPU. The project was developed at ByteDance Inc.
News
- [Nov 03 2021] Fixed a bug in train.py.
- [Sep 16 2021] Code is re-released under GPL-3.0 license.
- [Aug 25 2021] Source code and pretrained models are published.
- [Jul 27 2021] Paper is accepted by WACV 2022.
Showreel
Watch the showreel video (YouTube, Bilibili) to see the model's performance.
All footage in the video are available in Google Drive.
Demo
- Webcam Demo: Run the model live in your browser. Visualize recurrent states.
- Colab Demo: Test our model on your own videos with free GPU.
Download
We recommend MobileNetv3 models for most use cases. ResNet50 models are the larger variant with small performance improvements. Our model is available on various inference frameworks. See inference documentation for more instructions.
| Framework | Download | Notes |
| PyTorch |
rvm_mobilenetv3.pth rvm_resnet50.pth | Official weights for PyTorch. Doc |
| TorchHub | Nothing to Download. | Easiest way to use our model in your PyTorch project. Doc |
| TorchScript |
rvm_mobilenetv3_fp32.torchscript rvm_mobilenetv3_fp16.torchscript rvm_resnet50_fp32.torchscript rvm_resnet50_fp16.torchscript | If inference on mobile, consider export int8 quantized models yourself. Doc |
| ONNX |
For agents
This page has a .md twin and JSON over the API.