This algorithm is similar to what’s used in deepfake videos, and what self-driving cars use to “imagine” road scenarios.Īlthough much of the discussion around the potential harms of deepfakes has centered on how this technology can be used to propagate political misinformation and propaganda, it appears that the threat isn’t going away anytime soon. Pix2pix uses generative adversarial networks (GANs), which work by training an algorithm on a huge dataset of images – in the case of DeepNude, more than 10,000 nude photos of women, the developer said – and then trying to improve against itself.
(Source /en_us/article/kzm59x/deepnude-app-creates-fake-nudes-of-any-woman) That the software is based on pix2pix, an open-source algorithm developed by University of California, Berkeley researchers in 2017.
Programmers created an application that uses Neural Networks and Machine Learning to remove clothing from the images of women, making them look realistically nude.
0 kommentar(er)
