[This Gizmodo story describes how using artificial intelligence to enhance a famous “actuality” film from the dawn of cinema said to have evoked intense presence responses at the time makes it look “like it could have been shot just yesterday on a smartphone or a GoPro” and alters the viewing experience. The original story includes both version of the film. Coverage in The Next Web adds that “The video’s also had sound added, which makes it all the more eerily… normal,” and references an article in The Moving Image (via ResearchGate) about reactions to the original film. A commenter on an Ars Technica story notes that the new version is based on an already “highly processed digital restoration” and provides a link to the unrestored version. Scroll.In has the latest enhanced version at this writing, a colorized “DeOldified” version. And Boing Boing links to a 2012 remake. –Matthew]
[Image: Source: The Next Web]
Neural Networks Upscale Film from 1896 to 4K, Make It Look Like It Was Shot on a Modern Smartphone
Andrew Liszewski
February 4, 2020
There are lots of valid reasons to be worried about how deep learning techniques could potentially be used to manipulate footage for nefarious reasons. But as Denis Shiryaev demonstrates by upscaling some old black and white film footage from 1896, those AI-powered tools can also be a powerful way to bring the past back to life.
When watching old film footage that’s plagued with excessive amounts of grain, gate weave, soft focus, and a complete lack of color, it’s hard to feel connected to the people in the clip, or what’s going on. It looks like a movie, and over the years that medium has taught our brains that what they’re seeing on screen might not actually be real. By comparison, the experience of watching videos of friends and family captured on your smartphone is completely different thanks to 4K resolutions and high frame-rates. Those clips feel more authentic and while watching them there’s more of a connection to the moment, even if you weren’t actually there while it was being shot.
In 1896, Louis Lumière, one of the famous Lumière brothers who helped pioneer motion pictures and the equipment used to capture moving images on film, shot a short movie titled L’Arrivée d’un train en gare de La Ciotat which featured a train slowly chugging into a station. The short 45-second clip is most famous for several urban legends regarding moviegoers running out of the theater during showings back in 1896, terrified that an actual train was about to come plowing through the screen. Whether the film actually had that effect on early audiences may never be proven, but given how new and novel the medium was, the short clip certainly would have been a unique experience to someone who’d never seen moving footage before.
L’Arrivée d’un train en gare de La Ciotat doesn’t have the same effect on modern audiences, but Denis Shiryaev wondered if it could be made more compelling by using neural network powered algorithms (including Topaz Labs’ Gigapixel AI and DAIN) to not only upscale the footage to 4K, but also increase the frame rate to 60 frames per second. You might yell at your parents for using the motion smoothing setting on their fancy new TV, but here the increased frame rate has a dramatic effect on drawing you into the action.
Aside from it still being black and white (which could be dismissed as simply an artistic choice) and the occasional visual artifact introduced by the neural networks, the upgraded version of L’Arrivée d’un train en gare de La Ciotat looks like it could have been shot just yesterday on a smartphone or a GoPro. Even the people waiting on the platform look like the costumed historical reenactors you’d find portraying an old-timey character at a pioneer village. The results are far from perfect; we’re hoping Shiryaev applies one of the many deep learning algorithms that can colorize black and white photos to this film as well, but the obvious potential of these tools to enhance historical footage to increase its impact is just as exciting as the potential for it to be misused.
[via Digg]
Leave a Reply