NVIDIA Virtual Background
Updated: 2 Jun 2025
Generate a mask for an image using NVIDIA RTX to mask out human forms.
NVIDIA Virtual Background
Method #
This node uses NVIDIA’s Virtual Background technology running on NVIDIA RTX enabled GPUs to pick out human forms in video / images and remove them from the background, outputting a greyscale mask. This eliminates the need for green screen keying, allowing for use in much broader contexts.
The background removal is achieved using AI and was primarily developed by NVIDIA for use on webcam feeds, for video calls, and streaming, so has been trained primarily on those data sources. It will give the best results on video feeds that resemble those - e.g. front shots of a person’s head + shoulders. However, it still achieves good results on a much wider range of scenarios. A 16:9 aspect ratio input feed at HD resolution is recommended for best results.
Do not multi-parent this node. Multi-parenting breaks internal frame-to-frame coherence, resulting in significantly lower performance and reduced quality.
If your project contains multiple Virtual Background nodes, they must all use the same Quality Mode option. Mismatched settings can lead to significantly reduced performance.
In Notch versions later than 1.0.0.095, up to 8 Virtual Background node instances are supported across the entire block and all its instances. In earlier versions, the limit was 4.
This node requires NVIDIA Display Driver version 520.00 or higher as well as the installation of the NVIDIA Video Effects SDK and AR SDK, which can be downloaded here: NVIDIA Video Effects SDK
Make sure you get the correct driver for your GPU, Turing (20XX), Ampere (30XX) and Ada (40XX) use different drivers and they are not cross-compatible.
When using Disguise media servers please refer to this page for further information.
Parameters
These properties control the core behaviours of the node.
Parameter Details Active Turn the effect on or off. Values < 0.1 will turn the effect off.
Quality Mode Select the quality mode for the background removal.
- Best Quality (Slower) : The best quality, but lower performance. In this mode, the height of the input buffer must be greater than 360 pixels.
- Fastest Performance (Lower Quality) : The highest performance at a cost of lower quality output. In this mode, the height of the input buffer must be greater than 288 pixels.
These properties control the core behaviours of the node.
| Parameter | Details |
|---|---|
| Active | Turn the effect on or off. Values < 0.1 will turn the effect off. |
| Quality Mode | Select the quality mode for the background removal.
|
