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
- 'Perfectly real' deepfakes will arrive in 6 months to a year, technology pioneer Hao Li sayson September 20, 2019 at 7:14 pm
Everyday people will be able to create manipulated images and videos that seem "perfectly real" in "half a year to a year," industry pioneer Hao Li says. "Soon, it's going to get to the point where ...
- A fake interview with Vladimir Putin demonstrates how convincing deepfakes could be created in real-time in just a matter of yearson September 19, 2019 at 9:45 am
The artist behind the Putin cameo said deepfakes could be "perfect and virtually undetectable" within a few years, but we're not quite there yet.
- AI can't offer protection from 'deepfakes,' new report sayson September 18, 2019 at 4:34 pm
Artificial intelligence-based solutions may not be able to save us from deceptively altered videos, known as deepfakes, according to a new report from Data and Society. In the report, authors Britt ...
- Facebook Is Spending Millions To Try To Detect Deepfakeson September 17, 2019 at 9:33 pm
One of the big challenges facing tech companies today is the risk presented by "deepfake videos." In essence, deepfake videos are fake news in video format. They create a big problem because it's ...
- Deepfakes could anonymize people in videos while keeping their personalityon September 17, 2019 at 3:09 am
AI could generate faces that match the expressions of anonymous subjects to grant them privacy—without losing their ability to express themselves. The news: A new technique uses generative adversarial ...
- Scammers Go Phishing With Deepfakeson September 10, 2019 at 1:52 pm
I don't get a lot of questions about my job from my family. They are, understandably, far more interested in the hijinks of my rats and my dog. But when I do get asked about security, people ...
- Troll Watch: Deepfakes And 2020on September 8, 2019 at 2:04 pm
NPR's Michel Martin speaks with Paul Barrett, adjunct professor of law at NYU, about his report on what disinformation will look like in 2020 and what can be done to lessen its impact.
- Democrats face internal rancor over deep fakes, disinformationon September 7, 2019 at 3:43 am
Democrats are at war over disinformation. As illegitimate tactics like manipulated videos, troll farms, and fake social media accounts spread, state Democratic officials are demanding an official ...
- Facebook-led competition seeks new ways to identify deepfakes, but critics say it could backfireon September 6, 2019 at 5:00 pm
Facebook is spearheading a competition to find new ways to identify computer-altered videos known as deepfakes. But some artificial intelligence specialists say the strategy might backfire. Those ...
via Bing News