Nvidia AI could let you make video calls in your PJs without anyone knowing
The model could make videoconferencing marginally more bearable
GANimated video
Vid2Vid Cameo is powered bygenerative adversarial networks (GANs), which produce the videos by pitting two neural networks against each other: a generator that tries to create realistic-looking samples, and a discriminator that attempts to work out whether they’re real or fake.
This enables the two networks to synthesize realistic videos from a single image of the user, which could be a real photo or a cartoon avatar. During the video call, the model will capture their real-time motion and apply it to the uploaded image.
The model was trained on a dataset of 180,000 talking-head videos, which taught the network to identify 20 key points that encode the location of features including the mouth, eyes, and nose.
These points are then extracted from the image uploaded by the user to generate a video that mimics their appearance.
The model will be available soon in the Nvidia Maxine SDK and Nvidia Video Code SDK, but you can already try a demo of ithere. I gave it a go, and was pretty impressed by the system’s efforts — although I wouldn’t let it cut my hair.
You can read a research paper on the techniquehere.
Greetings Humanoids! Did you know we have a newsletter all about AI? You can subscribe to itright here.
Story byThomas Macaulay
Thomas is a senior reporter at TNW. He covers European tech, with a focus on AI, cybersecurity, and government policy.Thomas is a senior reporter at TNW. He covers European tech, with a focus on AI, cybersecurity, and government policy.
Get the TNW newsletter
Get the most important tech news in your inbox each week.
