Realtime background substraction for video or webcam using MobileNetV3. Model provided by https://github.com/PeterL1n/RobustVideoMatting
Shout out to Natxopedreira 2021 for providing the initial example.
Please check out the official documentation for this model.
Starting with the Turing architecture (e.g. RTX 2070), GPUs can utilize the FP16 data type and are therefore much faster!
The table provides a general guideline. Please adjust based on your video content.
| Resolution | Portrait | Full-Body |
|---|---|---|
| <= 512x512 | 1 | 1 |
| 1280x720 | 0.375 | 0.6 |
| 1920x1080 | 0.25 | 0.4 |
| 3840x2160 | 0.125 | 0.2 |
Internally, the model resizes down the input for stage 1. Then, it refines at high-resolution for stage 2.
Set downsample_ratio so that the downsampled resolution is between 256 and 512. For example, for 1920x1080 input with downsample_ratio=0.25, the resized resolution 480x270 is between 256 and 512.