Question of the Day - 28 April 2025

On August 28, a new version of The Wizard of Oz will debut at Sphere.

As for the process, one published account we read put it this way. "For months, thousands of researchers, programmers, visual-effects artists, archivists, and producers at Google DeepMind, Google Cloud, Sphere Studios, Magnopus, Warner Bros. Discovery, and others in the film and technology industries have been working to bring the 1939 classic to a very big screen in a very big way."

And that doesn't include all the generative AI used to reconceptualize the movie.

From what we understand, AI is such a major leap from conventional CGI (computer-generated imagery) that the undertaking would have been "nearly impossible," according to one film writer, even a few years ago. Imagen, a Google AI model that generates photorealistic images from text prompts and a photo editing and culling tool for professional photographers, along with Veo, a second AI model developed by Google DeepMind for generating high-quality realistic videos, were involved. That allowed the creative teams to work with only the original material. The producers are making a big deal that nary a single line of dialogue or a note of music was added to enrich the Sphere version. 

Of course, not even AI can transform a 35-millimeter film shot in Technicolor 77 years ago to a screen that's 160,000 square feet. That required a collaboration with Sphere Studios and Magnopus, known for its visual effects and production technology for the film industry, including augmented and virtual reality production (such as in its work on The Mandalorian, Coco, and The Lion King). Dozens of FX artists from all over the world were also involved. 

Even then, the challenges seemed overwhelming at times. Here's how an article on GoogleBlog described it.

"Magnifying the original grainy images for Sphere’s 16K LED screen — the highest-resolution screen in the world — was the first but far from the only challenge. The team also had to account for all the camera cuts in a traditional film that remove characters from parts of certain scenes, which wouldn’t work at the new theatrical scale that was envisioned.

"Take the moment where the Cowardly Lion first pounces on his soon-to-be companions. The camera pans back and forth between the Scarecrow and Tin Man, with cuts to Dorothy hiding behind a tree in the distance. The experience at Sphere called for keeping all these elements together -- in hyper-realistic detail."

Hang onto your hats, because this now gets pretty technical.

First, Google and its partners had to develop technology to transform the teensy celluloid, frame by frame, into ultra-ultra-ULTRA-high definition imagery at a resolution previously unheard of. Then, they invented a tool to "outpaint," or expand the scope of the scenes; that filled in the empty spaces left over from the original camera cuts and the limits of the scene framing. Finally, they used "performance generation" to incorporate composites of the frames at the new supercolossal scale.

All told, the work had to achieve everything from the big-picture staging to the fine details of the original performances. 

In addition, the teams didn't rely solely on the finished original film product or even all the old footage, including outtakes. They also took a deep dive into the archives for supplemental material -- shooting script, production illustrations, photographs, set plans, and scores. All that was uploaded into Veo and the other AI programs to improve the quality of the outputs. 

Throughout the process, Warner Bros. was involved, making sure that the caliber, intent, and spirit of the original film were maintained.

We'll definitely review one of the world's most beloved movies as seen in the world's most advanced movie theater when the time comes later this summer.