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
- How to save important photos and video from the webon January 19, 2021 at 2:48 pm
We can’t say exactly why you want to save images, videos, social media posts, or other types of information from the internet. We can, however, guess that you’re probably doing it for personal, ...
- CES 2021 Numbers Protocol Leverages Blockchain to Fight AI DeepFakes, Fake News, and Disinformationon January 18, 2021 at 7:23 am
With the current rampant tampering of images and proliferation of fake news and disinformation, one cannot easily tell if an image is real anymore. Numbers Protocol solves this by providing tools to ...
- See Tobey Maguire replace Darth Maul in hilarious Star Wars deepfake videoon January 17, 2021 at 2:22 pm
Deepfakes are fake videos that convincingly show people appearing to do or say things they never did. In this deepfake video titled Darth Bully Maguire: Duel of the Fates, Maguire becomes Darth Bully ...
- Teens have never known a world without data sharing, and it's creating a false sense of securityon January 15, 2021 at 1:51 pm
Talking about the potential damage to credit scores might not hit the mark for a 17-year-old. But we have to find a way to educate our very online youth generation.
- 4 Predictions for a Post-Pandemic World in 2021 and Beyondon January 15, 2021 at 1:44 am
Covid-19 created the perfect storm for widespread change and innovation. These changes will create a whole new world in 2021.
- Three steps to help treat America’s debilitating information disorderon January 13, 2021 at 1:07 pm
Updated consumer protection rules and enforcement would allow agencies such as the Federal Trade Commission to crack down on deepfakes, fake accounts, hidden amplification and other clearly deceptive ...
- Covid-19 Passport from iProov and Mvine Moves Into Trial Phaseon January 12, 2021 at 4:47 pm
Mvine and iProov announce today their design for a simple, secure and widely recognized Covid-19 immunity and vaccination passport will now move into live testing. The Mvine-iProov passport enables a ...
- Cyber Daily: Social-Media Watchdogs Detect Signs of Ongoing Extremist Threat | Cyber Insurers Bore Into Ransomware Claimson January 12, 2021 at 6:35 am
Researchers at the Atlantic Council, Stanford Internet Observatory and elsewhere who feared violence before the U.S. Capitol riot now warn about additional events being planned online, WSJ Pro’s David ...
- Can the Government Regulate Deepfakes?on January 7, 2021 at 8:56 am
New technology makes it possible to create videos that show a person doing or saying anything the creator wants—and it’s not clear what U.S. law can do about it.
via Bing News