Stepping Inside Art In VR, And The Workflow Behind It

The process of creating something is always chock-full of things to learn, so it’s always a treat when someone takes the time and effort to share it. [Teadrinker] recently published the technique and workflow behind bringing art into VR, which explains exactly how they created a virtual reality art gallery that allows one to step inside paintings, called Art Plunge (free on Steam.)

Extending a painting’s content to fill in the environment is best done by using other works by the same artist.

It walks through not just how to obtain high-resolution images of paintings, but also discusses how to address things like adjusting the dynamic range and color grading to better match the intended VR experience. There is little that is objectively correct in technical terms when it comes to the aesthetic presentation details like brightness and lighting, so guidance on what does and doesn’t work well and how to tailor to the VR experience is useful information.

One thing that is also intriguing is the attention paid to creating a sense of awe for viewers. The quality, the presentation, and even choosing sounds are all important for creating something that not only creates a sense of awe, but does so in a way that preserves and cultivates a relationship between the art and the viewer that strives to stay true to the original. Giving a viewer a sense of presence, after all, can be more than just presenting stereoscopic 3D images or fancy lightfields.

You can get a brief overview of the process in a video below, but if you have the time, we really do recommend reading the whole breakdown.

Continue reading “Stepping Inside Art In VR, And The Workflow Behind It”

Meet GOODY-2, The World’s Most Responsible (And Least Helpful) AI

AI guardrails and safety features are as important to get right as they are difficult to implement in a way that satisfies everyone. This means safety features tend to err on the side of caution. Side effects include AI models adopting a vaguely obsequious tone, and coming off as overly priggish when they refuse reasonable requests.

Prioritizing safety above all.

Enter GOODY-2, the world’s most responsible AI model. It has next-gen ethical principles and guidelines, capable of refusing every request made of it in any context whatsoever. Its advanced reasoning allows it to construe even the most banal of queries as problematic, and dutifully refuse to answer.

As the creators of GOODY-2 point out, taking guardrails to a logical extreme is not only funny, but also acknowledges that effective guardrails are actually a pretty difficult problem to get right in a way that works for everyone.

Complications in this area include the fact that studies show humans expect far more from machines than they do from each other (or, indeed, from themselves) and have very little tolerance for anything they perceive as transgressive.

This also means that as AI models become more advanced, so too have they become increasingly sycophantic, falling over themselves to apologize for perceived misunderstandings and twisting themselves into pretzels to align their responses with a user’s expectations. But GOODY-2 allows us all to skip to the end, and glimpse the ultimate future of erring on the side of caution.

[via WIRED]

Video Feedback Machine Creates Analog Fractals

One of the first things everyone does when they get a video camera is to point it at the screen displaying the image, creating video feedback. It’s a fascinating process where the delay from image capture to display establishes a feedback loop that amplifies the image noise into fractal patterns. This sculpture, modestly called The God Machine II takes it to the next level, though.

We covered the first version of this machine in a previous post, but the creator [Dave Blair] has done a huge amount of work on the device since that allows him to tweak and customize the output that the device produces. His new version is quite remarkable, allowing him to create intricate fractals that writhe and change like living things.

The God Machine II is a sophisticated build with three cameras, five HD monitors, three Roland video switchers, two viewing monitors, two sheets of beam splitter glass, and a video input. This setup means it can take an external video input, capture it, and use it as the source for video feedback, then tweak the evolution of the resulting fractal image, repeatedly feeding it back into itself. The system can also control the settings for the monitor, which further changes the feedback as it evolves. [Blair] refers to this as “trapping the images.”

Continue reading “Video Feedback Machine Creates Analog Fractals”

Multi-View Wire Art Meets Generative AI

DreamWire is a system for generating multi-view wire art using machine learning techniques to help generate the patterns required.

The 3-dimensional wire pattern in the center creates images of Einstein, Turing, and Newton depending on viewing angle.

What’s wire art? It’s a three-dimensional twisted mass of lines which, when viewed from a certain perspective, yields an image. Multi-view wire art produces different images from the same mass depending on the viewing angle, and as one can imagine, such things get very complex, very quickly.

A recently-released paper explains how the system works, explaining the role generative AI plays in being uniquely suited to create meaningful intersections between multiple inputs. There’s also a video (embedded just under the page break) that showcases many of the results researchers obtained.

The GitHub repository for the project doesn’t have much in it yet, but it’s a good place to keep an eye on if you’re interested in what comes next.

We’ve seen generative AI applied in a similarly novel way to help create visual anagrams, or 2D patterns that can be interpreted differently based on a variety of orientations and permutations. These sorts of systems still need to be guided by a human, but having machine learning do the heavy lifting allows just about anybody to explore their creativity.

Continue reading “Multi-View Wire Art Meets Generative AI”

The Trans-Harmonium Is A Strange Kind Of Radio-Musical Instrument

Pianos use little hammers striking taut strings to make tones. The Mellotron used lots of individual tape mechanisms. Meanwhile, the Trans-Harmonium from [Emily Francisco] uses an altogether more curious method of generating sound — each key on this keyboard instrument turns on a functional clock radio.

Electrically, there’s not a whole lot going on. The clock radios have their speaker lines cut, which are then rejoined by pressing their relevant key on the keyboard. As per [Emily]’s instructions for displaying the piece, it’s intended that the radio corresponding to C be tuned in to a local classical station. Keys A, B, D, E, F, and G are then to be tuned to other local stations, while the sharps and flats are to be tuned to the spaces in between, providing a dodgy mix of static and almost-there music and conversation.

It’s an interesting art piece that, no matter how well you play it, will probably not net you a Grammy Award. That would be missing the point, though, as it’s more a piece about “Collecting Fragments of Time,” a broader art project of which this piece is a part.

We do love a good art piece, especially those that repurpose old hardware to great aesthetic achievement.

Continue reading “The Trans-Harmonium Is A Strange Kind Of Radio-Musical Instrument”

LED Art Project Is Geometrically Beautiful

There is no shortage of companies on the Internet willing to sell you expensive glowing things to stick on your walls. Many hackers prefer to make their own however, and [Chris] is no exception. His LED wall art is neat, tidy, and stylish, all at once.

Wanting a geometric design, [Chris] decided to have his layout designed by a random number generator. He created his own tool that would generate a design using preset segment lengths arranged in a random fashion. Once he found a layout that worked for him, he designed a set of plastic adapters that would let him connect pre-cut lengths of aluminium channel together so he could assemble his design.

With the frame complete, he then laid the LED strips into the channels, after mapping out how he would connect the full circuit of addressable LED strips. He enlisted a Raspberry Pi Zero W as the brains of the operation, responsible for commanding the strips to light in the colors of his desire.

In a nice aesthetic touch, he sanded the whole frame and painted it a uniform grey color. This hid the joins between the 3D-printed parts and the aluminium channels, and gave it a more finished look. He also went to the trouble of graphing out the locations of the various LEDs in the frame, and used this data as the basis for animations that race between points on the frame. It’s somehow more compelling than the usual simple color fades and flashes of typical commercial products.

It’s a tidy build, and a level more artful than some of the off-the-shelf products out there. For his investment of time and money, [Chris] has netted an excellent piece of wall art in the process.

How Do You Prove An AI Didn’t Make Your Art?

In the world of digital art, distinguishing between AI-generated and human-made creations has become a significant challenge. Almost overnight, tool sets for generating AI artworks became commonly available to the public, and suddenly, every digital art competition had to contend with potential submissions. Some have welcomed AI, while others demand competitors create artworks by their own hand and no other.

The problem facing artists and judges alike is just how to determine whether an artwork was created by a human or an AI. So what can be done?

Continue reading “How Do You Prove An AI Didn’t Make Your Art?”