VToonify: Controllable high-resolution portrait video style transfer

Also reviewed at Two minute papers with a few examples <a href="https:&#x2F;&#x2F;youtube.com&#x2F;watch?v=C9LDMzMRZv8">https:&#x2F;&#x2F;youtube.com&#x2F;watch?v=C9LDMzMRZv8</a> (hold on to your papers...)

Well it&#x27;s cool and all, but the results sit right at the very deepest part of the uncanny valley.

I wonder what the implementation into e.g live streaming would require.

I&#x27;m glad things are progressing, but it bugs me that AI is largely being innovated for the use of... things like this? I know this comment is a bit disparaging and minimizes greater achievements, and I apologize for that, but the closeness of content-consumerism and AI is becoming quite off putting.

Based on the numbers in the paper this is just a little bit too slow for use as a real time video effect. At ~0.1 seconds per frame we just need about a 3x improvement in performance to get to 30fps “real time” video frame rates.<p>And on that thought since it appears they used nVidia hardware based on the CUDA dependency, it would be interesting to see how this performs on something like an M1&#x2F;M2 where there’s dedicated ML hardware to help offload and accelerate things.