Robust Video Matting - High Resolution Human Segmentation
NatML
$0.0
(no ratings)
|
Date |
Price |
|---|---|
|
日期和时间 |
价钱($) |
|
03/14(2022) |
0.0 |
|
11/18(2024) |
0.0 |
Jump AssetStore
High resolution human segmentation powered by machine learning.Perform high resolution human segmentation with the Robust Video Matting segmentation model from ByteDance (TikTok). This package requires the open source NatML library to run the machine learning model. Features include:+ Bare Metal Performance. The Robust Video Matting predictor is implemented with NatML, which takes advantage of hardware machine learning accelerators, like CoreML on iOS and macOS, NNAPI on Android, and DirectML on Windows.+ Background Replacement. The Robust Video Matting predictor accepts an image and returns a segmentation matte. This matte can be rendered into a `RenderTexture`, allowing for building custom shader effects like background replacement. See more on NatML Hub.+ Cross Platform. The Robust Video Matting predictor supports Android, iOS, macOS, and Windows alike, allowing you to develop in the Editor and deploy to device in one seamless workflow.+ Lightweight Package. This package contains the predictor scripts, whereas the ML model will be downloaded at runtime from NatML Hub and cached onto the device, reducing the app size significantly.Discover more ML models on NatML Hub.Join the NatML community on Discord.Check out the NatML documentation.See more NatML projects on GitHub.Read the NatML blog.Discuss NatML on Unity Forums.Contact us at hi@natml.ai.Dependencies- NatML 1.0.11+Supported Platforms- Android API Level 24+ (Android Nougar or newer)- iOS 13+- macOS 10.15+- Windows 10+, 64-bit only
