Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
1–10 of 129 posts
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#2Am i reading that right? Its making the videos that look real, from the simplistic input?
If so, that is amazing.
And if so, how do I turn a video I have into a simple/line version, to be able to then put a different 'skin' on it?
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#3Am i reading that right? Its making the videos that look real, from the simplistic input? If so, that is amazing. And if so, how do I turn a video I have into a simple/line version, to be able to then put a different 'skin' on it?
With edge detection. Normally edge detection means looking for local sharp changes in brightness and marking them with a white spot. The edge detection used in this case looks more sophisticated to me. I don’t know how it works
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#4Am i reading that right? Its making the videos that look real, from the simplistic input? If so, that is amazing. And if so, how do I turn a video I have into a simple/line version, to be able to then put a different 'skin' on it?
You could try OpenCV Canny Edge Detection:
https://docs.opencv.org/3.1.0/da/d22/tutorial_py_canny.html
Example with video here https://www.youtube.com/watch?v=1Ndxtb0q76c
Obviously would need some tweaking but could be a good starting point
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#5Am i reading that right? Its making the videos that look real, from the simplistic input? If so, that is amazing. And if so, how do I turn a video I have into a simple/line version, to be able to then put a different 'skin' on it?
The level of realism can be gauged from the examples they provide right there on the page. Of course your results may vary basing on the initial bulk of data of realistic source images you use.
You have the code right there on Github, just install it on some PC with powerful GPUs (or rent one), tune some parameters, train the network and you can do the same things.
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#6Am i reading that right? Its making the videos that look real, from the simplistic input? If so, that is amazing. And if so, how do I turn a video I have into a simple/line version, to be able to then put a different 'skin' on it?
With edge detection. Normally edge detection means looking for local sharp changes in brightness and marking them with a white spot. The edge detection used in this case looks more sophisticated to me. I don’t know how it works
Looks just like edge detection + contouring from RGBD data.
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#7I'm probably being captain obvious here, but if this is what's being released for free, I wonder how much better a polished commercial version does, and when we reach the point where we can't trust anything we see anymore. It doesn't even have to be super perfect, even reaching the point where it takes experts about two weeks to determine if something's real or not might already be long enough to do great damage.
From a technical standpoint I think this is very impressive, and I'm also interested in creative/artsy use of this. Their "replace trees by houses" example is pretty dull but gives a good glimpse at what can be done.
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#8One of the example translates a full human pose to a video of a dancer. If the network would be trained on the facial pose(?) / features only, would that recreate something like the facial reenactment in http://niessnerlab.org/projects/thies2016face.html (source code for face2face is not public)?
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#9I'm probably being captain obvious here, but if this is what's being released for free, I wonder how much better a polished commercial version does, and when we reach the point where we can't trust anything we see anymore. It doesn't even have to be super perfect, even reaching the point where it takes experts about two weeks to determine if something's real or not might already be long enough to do great damage. Fro…
I'm sure the point is already crossed. People on 4chan are making fake porn that is nearly indistinguishable - and they are complete amateurs.
Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation
#10One of the example translates a full human pose to a video of a dancer. If the network would be trained on the facial pose(?) / features only, would that recreate something like the facial reenactment in http://niessnerlab.org/projects/thies2016face.html (source code for face2face is not public)?
Look into Deepfake, that's the tool 4chan is using for face swapping in their fake porn