Conan O’Brien will return to TV with shows shot on iPhone and over video chat

Published March 19, 2020

Apple’s promise of high-quality video “shot on iPhone” is getting another real-world stress test, as late-night TV host Conan O’Brien announced on Wednesday he will return to doing full shows that will be shot using Apple’s mobile device. On Monday, March 30, new episodes of O’Brien’s show “Conan” will air on TBS, with production staff working from home, video that’s shot on iPhone and interviews filmed over video chat.

The news was first reported by Variety and confirmed by O’Brien in the form of a tweet, where he jokes the experience “will not be pretty.”

I am going back on the air Monday, March 30th. All my staff will work from home, I will shoot at home using an iPhone, and my guests will Skype. This will not be pretty, but feel free to laugh at our attempt. Stay safe.

— Conan O’Brien (@ConanOBrien) March 19, 2020

The move to shoot shows remotely is an interesting attempt at restarting daily TV production at a time when everyone’s been ordered to work from home.

Typically, late-night shows are put on with a sizable crew of writers and producers and filmed in front of a live audience. With the CDC advising people to stay at home and gather in groups of no more than 10 due to the threat of the coronavirus outbreak, TV production industry-wide is being shut down.

Until now, that also included all major late-night productions, like Stephen Colbert, Jimmy Fallon, Jimmy Kimmel and James Corden .

O’Brien’s team consists of 75 people and, like others, it went on hiatus in order to protect staff safety. But during the shut down, O’Brien continued to film short videos, which led the team to this idea of doing a full show, but in a different format.

“Conan” isn’t the only show trying to work around the shutdown. Jimmy Fallon has been filming YouTube videos that are incorporated into the evening’s rerun of the “Tonight Show.” Colbert has been filming a new monologue for “The Late Show” reruns. And Kimmel has been sharing his own “#minilogue” on social media.

However, “Conan” is promising full episodes, not just new segments.

“The quality of my work will not go down because technically that’s not possible,” O’Brien said in a statement shared by Variety.

Image credit: Kevin Mazur/Getty Images for WarnerMedia

This tech (scarily) lets video change reality

Published September 11, 2018

Researchers at Carnegie Mellon University have created a method to turn one video into the style of another. While this might be a little unclear at first, take a look at the video below. In it, the researchers have taken an entire clip from John Oliver and made it look like Stephen Colbert said it. Further, they were able to mimic the motion of a flower opening with another flower.

In short, they can make anyone (or anything) look like they are doing something they never did.

“I think there are a lot of stories to be told,” said CMU Ph.D. student Aayush Bansal. He and the team created the tool to make it easier to shoot complex films, perhaps by replacing the motion in simple, well-lit scenes and copying it into an entirely different style or environment.

“It’s a tool for the artist that gives them an initial model that they can then improve,” he said.

The system uses something called generative adversarial networks (GANs) to move one style of image onto another without much matching data. GANs, however, create many artifacts that can mess up the video as it is played.

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.

The researchers created something called Recycle-GAN that reduces the imperfections by “not only spatial, but temporal information.”

“This additional information, accounting for changes over time, further constrains the process and produces better results,” wrote the researchers.

Recycle-GAN can obviously be used to create so-called Deepfakes, allowing for nefarious folks to simulate someone saying or doing something they never did. Bansal and his team are aware of the problem.

“It was an eye opener to all of us in the field that such fakes would be created and have such an impact. Finding ways to detect them will be important moving forward,” said Bansal.