Nvidia’s New AI Can Generate Mind-Blowing Fake Videos
Events
Subscribe:  iCal  |  Google Calendar
Los Angeles US   27, Sep — 1, Oct
Moscow RU   4, Oct — 8, Oct
Prague CZ   5, Oct — 7, Oct
São Paulo BR   10, Oct — 15, Oct
Latest comments
by khiree.taylan
47 min ago

is this project showed on android mobile phone or super pc??

by eizenhorn91@mail.ru
11 hours ago

Angelin, it is NOT HD Render Pipeline, it is legacy Unity render path.

by Tristan
23 hours ago

Hi how long have you been making 3D art and models i have started this year and you work is great I have learned a lot but no where near your knowledge Do you have any suggestions or tips to speed up my workflow and quality. I am also working on a game in ue4 with 2 other people which is going to be a long project and do you have any recommendations on performance and quality Would greatly appreciate it Thanks

Nvidia’s New AI Can Generate Mind-Blowing Fake Videos
6 December, 2017
News

Nvidia has recently presented an AI that with an unsupervised learning method for computers which can create mind-blowing fake videos. The system will allow users to set up weather, turn day into night, and change almost anything. 

Previous techniques relied on massive amounts of data and has problems with training the machines to find their own patterns. Researched had a hard time dealing with mapping a low-resolution image to a corresponding high-resolution image and colorization (mapping a gray-scale image to a corresponding color image).

Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions. To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs. We compare the proposed framework with competing approaches and present high quality image translation results on various challenging unsupervised image translation tasks, including street scene image translation, animal image translation, and face image translation. We also apply the proposed framework to domain adaptation and achieve state-of-the-art performance on benchmark datasets. Code and additional results are available in this https URL .

Ming-Yu LiuThomas BreuelJan Kautz 

Read the paper

The modern machines can turn sunny days into rainy ones, create the equivalent of a “snow plow” filter for videos, and more. 

Reality is now a strange thing thanks to projects of Nvidia. Should we be worried? Let’s discuss!

Leave a Reply

Be the First to Comment!

avatar
wpDiscuz