Transforming Video Content Into Another Video’s Style, Automatically
Researchers at Carnegie Mellon University have devised a way to automatically transform the content of one video into the style of another, making it possible to transfer the facial expressions of comedian John Oliver to those of a cartoon character, or to make a daffodil bloom in much the same way a hibiscus would.
Because the data-driven method does not require human intervention, it can rapidly transform large amounts of video, making it a boon to movie production. It can also be used to convert black-and-white films to color and to create content for virtual reality experiences.
“I think there are a lot of stories to be told,” said Aayush Bansal, a Ph.D. student in CMU’s Robotics Institute. Film production was his primary motivation in helping devise the method, he explained, enabling movies to be produced more quickly and cheaply. “It’s a tool for the artist that gives them an initial model that they can then improve,” he added.
The technology also has the potential to be used for so-called “deep fakes,” videos in which a person’s image is inserted without permission, making it appear that the person has done or said things that are out of character, Bansal acknowledged.
“It was an eye opener to all of us in the field that such fakes would be created and have such an impact,” he said. “Finding ways to detect them will be important moving forward.”
Transferring content from one video to the style of another relies on artificial intelligence. In particular, a class of algorithms called generative adversarial networks (GANs) have made it easier for computers to understand how to apply the style of one image to another, particularly when they have not been carefully matched.
In a GAN, two models are created: a discriminator that learns to detect what is consistent with the style of one image or video, and a generator that learns how to create images or videos that match a certain style. When the two work competitively — the generator trying to trick the discriminator and the discriminator scoring the effectiveness of the generator — the system eventually learns how content can be transformed into a certain style.
A variant, called cycle-GAN, completes the loop, much like translating English speech into Spanish and then the Spanish back into English and then evaluating whether the twice-translated speech still makes sense. Using cycle-GAN to analyze the spatial characteristics of images has proven effective in transforming one image into the style of another.
That spatial method still leaves something to be desired for video, with unwanted artifacts and imperfections cropping up in the full cycle of translations. To mitigate the problem, the researchers developed a technique, called Recycle-GAN, that incorporates not only spatial, but temporal information. This additional information, accounting for changes over time, further constrains the process and produces better results.
The researchers showed that Recycle-GAN can be used to transform video of Oliver into what appears to be fellow comedian Stephen Colbert and back into Oliver. Or video of John Oliver’s face can be transformed into a cartoon character. Recycle-GAN allows not only facial expressions to be copied, but also the movements and cadence of the performance.
The effects aren’t limited to faces, or even bodies. The researchers demonstrated that video of a blooming flower can be used to manipulate the image of other types of flowers. Or clouds that are crossing the sky rapidly on a windy day can be slowed to give the appearance of calmer weather.
Such effects might be useful in developing self-driving cars that can navigate at night or in bad weather, Bansal said. Obtaining video of night scenes or stormy weather in which objects can be identified and labeled can be difficult, he explained. Recycle-GAN, on the other hand, can transform easily obtained and labeled daytime scenes into nighttime or stormy scenes, providing images that can be used to train cars to operate in those conditions.
Learn more: Beyond Deep Fakes
The Latest on: Deep fakes
via Google News
The Latest on: Deep fakes
Facebook and Twitter will testify on terrorist content, report says
on June 19, 2019 at 12:17 pm
The spread of misinformation has also been a hot topic, particularly in the run-up to the 2020 presidential election, with deepfakes, fake news and doctored media being spread across social media. ... […]
Can Anything Protect Us From Deepfakes?
on June 19, 2019 at 6:47 am
In late 2017, Motherboard reported on an AI technology that could swap faces in videos. At the time, the tech—later called deepfakes—produced crude, grainy results and was mostly used to create fake ... […]
Hany Farid: Deepfakes give new meaning to the concept of 'fake news,' and they're here to stay
on June 18, 2019 at 1:15 am
Rumors quickly spread in Trent, Italy that members of the Jewish community murdered a young boy and drained and drank his blood to celebrate Passover. Before long, the city’s entire Jewish community ... […]
New software designed to help media detect deepfakes – but it's just a "drop in the bucket"
on June 17, 2019 at 8:00 am
Tech experts are gathering in Southern California to fight the growing threat of so-called deepfakes – videos that are manipulated to change their message, or even who appears in them. While some of ... […]
Deepfakes are dangerous — and they target a huge weakness
on June 16, 2019 at 4:24 pm
DEEPFAKES ARE dangerous — not only the synthetic videos themselves but also the way they promise to blur reality in a country where facts are already up for debate. Congress held a hearing last week ... […]
Recommended Reading: Fighting deepfakes
on June 15, 2019 at 9:30 am
The 2016 US presidential election was plagued by fake news and election meddling across the internet. With the rise of so-called deepfake technology, fact-checkers and arbiters of truth face a new ... […]
Biden says he won’t use bots, disinformation, deepfakes
on June 14, 2019 at 3:53 pm
Former vice president Joe Biden on Friday pledged not to use illicit campaign tactics or spread disinformation in his run for the presidency, and called on other candidates to do the same. The pledge ... […]
Deepfakes may be a useful tool for spies
on June 14, 2019 at 1:38 pm
A spy may have used an AI-generated face to deceive and connect with targets on social media. The news: A LinkedIn profile under the name Katie Jones has been identified by the AP as a likely front ... […]
Biden: No deep fakes, bots or disinformation by my campaign
on June 14, 2019 at 8:41 am
Joe Biden is pledging to not take part in the spread of disinformation over social media in his campaign for president, including rejecting the use of deep fake videos, synthetic social media accounts ... […]
via Bing News