Software developer Adobe has introduced the Project In-Between and Project Morpheus tools to bring photos to life and create deepfakes. The demonstration took place at the Max Design Conference.
Project Morpheus is feature based Neural Filterspresented in 2020. The tool is capable of automating frame-by-frame video editing in such a way as to get stable results, the company said.
In the demo, an Adobe employee edited a video of his own, which changed from a neutral expression to a smile. According to him, the process took a matter of seconds, and most of the work was done by the AI algorithm Adobe Sensei.
Project In-Between allows you to create short, realistic animation from two or more images, similar to live photos on iOS devices. In this case, the photographs should be similar to each other, for example, a series of shots of one scene.
Adobe says the feature can also be applied to videos to create slow-motion videos.
It is not known whether experimental tools will appear for the general public. In company statedthat not all features shown may make it to release:
“Project Morpheus is a way to familiarize ourselves with the research and emerging technologies of our laboratories and engineering teams. These experimental ideas are not always meant to be incorporated into products. ”
The company stressed that they are aware of the importance of combining innovation with responsibility “so that technologies are used for the benefit of our customers and society.”
“We are guided by the principles of accountability, responsibility and transparency in developing AI,” they added.
Recall that in September, scientists told how to distinguish a real photo from a deepfake.
In August, Megafon used a fake Bruce Willis in a promotional video.
In April, genealogy company MyHeritage used AI to teach live photography to dance and blow a kiss.
Subscribe to Cryplogger news on Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL + ENTER
Software developer Adobe has introduced the Project In-Between and Project Morpheus tools to bring photos to life and create deepfakes. The demonstration took place at the Max Design Conference.
Project Morpheus is feature based Neural Filterspresented in 2020. The tool is capable of automating frame-by-frame video editing in such a way as to get stable results, the company said.
In the demo, an Adobe employee edited a video of his own, which changed from a neutral expression to a smile. According to him, the process took a matter of seconds, and most of the work was done by the AI algorithm Adobe Sensei.
Project In-Between allows you to create short, realistic animation from two or more images, similar to live photos on iOS devices. In this case, the photographs should be similar to each other, for example, a series of shots of one scene.
Adobe says the feature can also be applied to videos to create slow-motion videos.
It is not known whether experimental tools will appear for the general public. In company statedthat not all features shown may make it to release:
“Project Morpheus is a way to familiarize ourselves with the research and emerging technologies of our laboratories and engineering teams. These experimental ideas are not always meant to be incorporated into products. ”
The company stressed that they are aware of the importance of combining innovation with responsibility “so that technologies are used for the benefit of our customers and society.”
“We are guided by the principles of accountability, responsibility and transparency in developing AI,” they added.
Recall that in September, scientists told how to distinguish a real photo from a deepfake.
In August, Megafon used a fake Bruce Willis in a promotional video.
In April, genealogy company MyHeritage used AI to teach live photography to dance and blow a kiss.
Subscribe to Cryplogger news on Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL + ENTER
