Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v...
by magnat on Saturday September 22, 2018 @06:34AM
(#18045411)
> Photo-realistic games. Create a rough 3D model of an scenario and train the AI for it. Instead of photo-realistic rendering with math, render it with the AI based on a rough render, in real-time.
According to last month's nvidia rtx presentation/launch event [1], they are going to do something similar quite soon. Games will ship with DNN pre-trained offline on extremely high quality renderings. Game itself renders at lower resolution (limited by performance needed for proper raytracing) and uses DNN to upscale it.
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v...
by antpls on Saturday September 22, 2018 @11:15AM
(#18046295)
I wonder, since the NN cores of the GPU are used for real-time raytracing, will they be able to run custom NNs possibly not related to visual stuff in parallel to the ray-tracing stuff?
Edit : found the answer on Internet, apparently the RT (raytracing) cores are different and separated from the Tensor (NN) cores on the RTX
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v...
by 21 on Saturday September 22, 2018 @12:14PM
(#18046551)
I think this is about trading storage for computation - you replace terabytes of model/texture data with a compute heavy NN.
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v...
by kmlx on Saturday September 22, 2018 @06:45AM
(#18045442)
any ideas about porn startups that work on anything related to this?
i know pornhub and their network banned deepfakes and there’s also some work being done on detecting deepfakes.
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v...
by Findeton on Saturday September 22, 2018 @07:34AM
(#18045588)
Nayghty America:
https://www.theverge.com/2018/8/21/17763278/deepfake-porn-cu...
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v...
by grif-fin on Saturday September 22, 2018 @07:46AM
(#18045625)
> Propaganda and misinformation. Now you can get your enemy to say and do whatever you want, on video.
This could open the market for video propaganda-detector applications.
- Porn, yeah, first application you can think of, there are already some startups doing it.
- Doubling actors, and applied to sound, maybe you could translate from one language to another but kind of keeping the accent and tone.
- Propaganda and misinformation. Now you can get your enemy to say and do whatever you want, on video.
- Photo-realistic games. Create a rough 3D model of an scenario and train the AI for it. Instead of photo-realistic rendering with math, render it with the AI based on a rough render, in real-time.