When I was a kid growing up in rural Yorkshire, one of the regular attractions at local fairs was a huge steam-powered organ: a baroque monstrosity of pipes, horns, and whistles that would parp out classical tunes to the delight of onlookers. I don’t know if steam organs are still a thing, but if they’ve been retired then I have the perfect replacement: the Floppotron — a mammoth “PC hardware orchestra” that plays music using only electric motors.

Like a fairground organ, the Floppotron is unwieldy, massive, musically unsubtle, and a complete joy to behold. It’s the work of Polish engineer Paweł Zadrożniak, who’s been building various iterations of the instrument since 2011. The first Floppotron consisted of just a pair of floppy drives playing The Imperial March from Star Wars, but its most recent incarnation — Floppotron 3.0 — contains a full orchestra of PC peripherals: 512 floppy disk drives, 16 hard drives, and four flatbed scanners. It is immense.

The concept behind the Floppotron is simply that electric motors make noise. Tune exactly how fast and hard you run the motor (its frequency) and you can produce specific notes. Combine enough of those notes and, voila, you have music.

Image: Paweł Zadrożniak

As Zadrożniak explains in a detailed blog post on the Floppotron 3.0, the system has now become incredibly complex. The floppy disk drive wall is arranged into columns, each of which handles a single note at a time, with the number of drives engaged varying the sound envelope (how loud or soft it is; how much vibrato it has, and so on). These floppy disk drives handle the low tones, while the scanner section uses the scanners’ larger motors to provide the higher pitches. A group of hard disk drives rounds things out as the percussion section, with bangs and clicks enunciated by drive heads moving across disk platters.

The Floppotron is a work of art, really, and I can only hope Zadrożniak continues with his work and maybe inspires some imitators, too. Who knows, in 50 years’ time, maybe one of Floppotron’s heirs will be entertaining small children at a fair the way steam organs fascinated me.

Nvidia’s latest AI demo is pretty impressive: a tool that quickly turns a “few dozen” 2D snapshots into a 3D-rendered scene. In the video below you can see the method in action, with a model dressed like Andy Warhol holding an old-fashioned Polaroid camera. (Don’t overthink the Warhol connection: it’s just a bit of PR scene dressing.)

The tool is called Instant NeRF, referring to “neural radiance fields” — a technique developed by researchers from UC Berkeley, Google Research, and UC San Diego in 2020. If you want a detailed explainer of neural radiance fields, you can read one here, but in short, the method maps the color and light intensity of different 2D shots, then generates data to connect these images from different vantage points and render a finished 3D scene. In addition to images, the system requires data about the position of the camera.

Researchers have been improving this sort of 2D-to-3D model for a couple of years now, adding more detail to finished renders and increasing rendering speed. Nvidia says its new Instant NeRF model is one of the fastest yet developed and reduces rendering time from a few minutes to a process that is finished “almost instantly.”

As the technique becomes quicker and easier to implement, it could be used for all sorts of tasks, says Nvidia in a blog post describing the work.

“Instant NeRF could be used to create avatars or scenes for virtual worlds, to capture video conference participants and their environments in 3D, or to reconstruct scenes for 3D digital maps,” writes Nvidia’s Isha Salian. “The technology could be used to train robots and self-driving cars to understand the size and shape of real-world objects by capturing 2D images or video footage of them. It could also be used in architecture and entertainment to rapidly generate digital representations of real environments that creators can modify and build on.” (Sounds like the metaverse is calling.)

In a paper describing the work, Nvidia’s researchers said they were able to export scenes at a resolution of 1920 × 1080 “in tens of milliseconds.” The researchers also shared source code for the project, allowing others to implement their methods. It seems NeRF renders are progressing quickly, and could start having a real-world impact in the years to come.

Update March 25th, 15:50PM ET: Updated story with link to research paper and source code.