Nvidia Uses AI to Slash Bandwidth on Video Calls
petapixel.com
Nvidia Uses AI to Slash Bandwidth on Video Calls
1–10 of 197 posts
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#2Wonderful technical achievement but I think I’d rather squint through garbled video to see a real human.
Now if I can use it to add a Klingon skull ridge and hollow eyes to my boss or scribble notes on my scrum master’s generous forehead we might be on to something.
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#3I hope they use this kind of tech for the Shield TV, too, to make 360p/480p videos look like 1080p/4k in the next few years.
This would drastically set the Shield TV apart from any other "smart" TV or set top box. People would want to buy a Shield just for this feature alone. The DLSS for games is already (over) hyped, but this would make much more sense for videos and TV.
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#4Nvidia Uses AI to Slash Bandwidth on Video Calls... But only if everybody in the call has a 600$ Nvidia GPU
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#5Is it just me or do the videos no longer look natural? I feel like I see highly non-linear movements (parts of the video moving when they shouldn't, or vice-versa), and facial expressions don't really look quite the same.
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#6We're all deepfakes now, it seems.
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#7Stills OK, it would be interesting to see it move. Risk for uncanny valley?
Petapixel is a blog spam site btw. Why not go to the source that is linked in the post?
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#8Nvidia Uses AI to Slash Bandwidth on Video Calls... But only if everybody in the call has a 600$ Nvidia GPU
Depends on how big the network is. You can process neural networks on CPU with acceptable speed in certain cases. And nicer smart phones tend to have a decent GPU.
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#9Is it just me or do the videos no longer look natural? I feel like I see highly non-linear movements (parts of the video moving when they shouldn't, or vice-versa), and facial expressions don't really look quite the same.
fair, in that they aren't perfect photorealism, but if their comparisons with the regular codecs and techniques are correct, I'd take their modelled faces over the comparable- level of digital artifacts for the same bandwidth.
After all, it doesn't need to be said that when you're on a regular videoconferencing call and bandwidth starts to suffer, the resulting images don't really look anything like a photorealistic person either. I think this is actually a really good use of NN.
Re: Nvidia Uses AI to Slash Bandwidth on Video Calls
#10Is it just me or do the videos no longer look natural? I feel like I see highly non-linear movements (parts of the video moving when they shouldn't, or vice-versa), and facial expressions don't really look quite the same.
fair, in that they aren't perfect photorealism, but if their comparisons with the regular codecs and techniques are correct, I'd take their modelled faces over the comparable- level of digital artifacts for the same bandwidth. After all, it doesn't need to be said that when you're on a regular videoconferencing call and bandwidth starts to suffer, the resulting images don't really look anything like a photorealistic…
The thing is you only want to make this trade-off when the bandwidth is actually starting to suffer. It'd be nice if there was a nice way to make this adaptive and use NNs only when throughput is low, but the nonlinearity of the distortions makes me think this would be really hard. [1] I know what I don't want is for a normal conversation in an uncongested network to look unnatural or for facial expressions to get distorted unnecessarily.
Edit: [1] I meant to say doing a mixture of these (with the NN image as the "base", with H.264 to improve accuracy) seems really hard. On the other hand, just a hard switch from H.264 to NN when quality degrades is probably quite practical?