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
- Deepfakes are getting better. Should we be worried?on December 14, 2019 at 6:36 am
And what we now call deepfakes were born. These doctored videos that use deep learning algorithms (this is the “deep”) to produce synthetic imagery and voice (the “fake”) warp images and videos ...
- The Technology 202: Businesses should be watching out for deepfakes too, experts warnon December 13, 2019 at 6:15 am
Fake videos doctored by artificial intelligence are not just a threat to politicians in 2020. Corporate brands should be on alert for "deepfakes" too, experts are warning. Chief executives including ...
- How Deepfakes Scramble Our Sense of True and Falseon December 6, 2019 at 11:00 pm
Preiss had placed the call using a software clone of her voice made to demonstrate artificial intelligence’s ability to deceive. Fake videos known as deepfakes are powerful examples of how AI can ...
- ‘Deep fakes’ pose threat for students when identifying online informationon December 6, 2019 at 3:24 pm
A survey by Stanford researchers found that students are unprepared to judge the credibility of information from the internet. Sam Winebuurg, founder and executive director of the Standford University ...
- Training algorithms to recognize deep fakeson December 5, 2019 at 6:15 am
Christye Sisson, professor and director of photographic sciences at the Rochester Institute of Technology, talks to Tonya Hall about the process of recognizing deep fakes, along with the importance of ...
- Can you tell which face is real? UW and WSU plan to fight digital ‘deepfakes’on December 4, 2019 at 5:00 am
If you were under any illusion that online hooey peaked with the 2016 election, brace yourself for the era of “deepfakes” — fabricated videos so realistic they can put words in the mouths of ...
- Text-Based Deepfakes, Model Hacking Among Top AI Threatson December 3, 2019 at 3:11 pm
Companies should brace themselves for two emerging threats related to artificial intelligence: text-based deepfakes and AI model hacking, cybersecurity experts said.
- China Makes Deepfakes and Fake News Illegalon December 2, 2019 at 5:37 am
Internet regulators in China have now banned fake news and fake video content including deepfakes. As reported by Reuters, the Cyberspace Administration of China said that any use of virtual reality ...
- China is trying to prevent deepfakes with new law requiring that videos using AI are prominently markedon November 30, 2019 at 10:17 am
Deepfake videos are notoriously difficult to detect, and it's unclear how China will enforce the new law that will go into effect on January 1, 2020.
via Bing News