One of the most striking contributions of artificial intelligence to advanced computer programming is architectural visualization. This can be seen and experienced, among other things, in two new apps that are simply stunning, even if you think you’ve seen it all.
The first is called Canvas and is the brainchild of Nvidia, the world’s leading designer and manufacturer of graphics processors for computers. It’s hard, in words alone, to give a full picture of what Canvas can do. A better way would be to watch the videos available on YouTube on the subject.
Even Nvidia’s own definition doesn’t describe the app’s spectacular work; it “allows you to customize your image so that it matches exactly what you need. The canvas has nine styles that change the look and feel of a painting and twenty different materials ranging from sky and mountains to river and stone. Paint on different layers to keep the elements separate. You can start from scratch or take inspiration from one of the example scenes”.
In simpler terms, perhaps, without having any special skills in drawing, painting, photography or design, you use the mouse and apply rough and rough brush strokes on a blank window on your screen, select one of nine styles mentioned above (mountain, sky, etc.), and Canvas almost instantly transforms them into real places, objects, landscapes, as surely as if they were photographs of the real place, object or landscape . Once the target is created, you can customize, refine, and modify it to your liking or to the requirements of the project you’re working on. It’s done at lightning speed and the result is as realistic as taking a photo – and a great photo – of a real place or landscape.
Dall-E-2 is the other app, and it works differently. No brush strokes here. You just describe, in words, in plain text, the landscape you have in mind, and Dall-E-2 will generate the photo you have in mind. For example, type “a detached house, with brick walls, a swimming pool, a small red car in the garage, a dog in the garden, and a cloudy sky above”, and watch the result on the screen, as photo realistic as in real life.
As with Canvas, watching relevant videos on YouTube gives a clear idea of the app’s power.
Customization, with minute details, is also possible here. Edit the text you started from, and the image will follow, render, and apply the edit. You can even add people, flowers or furniture. It is, again, the power of software programming combined with AI algorithms that does the trick. This would have been unthinkable just 10 years ago.
Jordanian designer Yazan Baggili, who recently downloaded and experimented with Canvas in his office, explained that “Canvas is basically about creating backgrounds and landscapes. Dalle-E-2 is more about visualizing things that are only in your mind, such as: a cat in space in the style of Van Gogh!
It is, again, the power of software programming combined with AI algorithms that does the trick. This would have been unthinkable just 10 years ago.
Jordan News he added, “We are slowly but surely getting used to the way AI accesses gigantic databases of nearly every type of content. Now Canvas and Dall-E-2 can harness these resources and create things that have never existed before, combining them in artistic and stunning ways.
To quickly name a third player in the game, Unreal 5 is another architectural visualization software that does incredible photorealistic renderings.
It is understood that such applications require a fast computer processor, such as the Intel i7 type, and a powerful graphics processor as well, such as the latest generation Nvidia. Failure to comply with these technical requirements may simply prevent the software from working or may even make it impossible to install such applications.
We are only just beginning to feel the effects of AI-injected software in practical and tangible ways, either in very positive ways, or in negative ways, such as in crashes and prediction errors. In extreme cases it can be tragic, at other times simply entertaining.
A negative example: “U.S. automakers reported nearly 400 crashes involving cars equipped with partially autonomous driver assistance systems, according to a new report from a U.S. auto safety regulator released Wednesday,” Al Jazeera on June 15.
A lighter example is the amused reaction of Carlos Alija, executive creative director at MullenLowe, an American advertising and marketing communications agency, to how tennis champion Rafael Nadal rallied from two sets to win the Australian Open last January when AI algorithms gave opponent Daniil Medvedev a 96% chance of winning in the 3rd set.
My first formal and academic approach to AI dates back to 1983 when I was studying the textbook titled “Artificial Intelligence” by Elaine Rich from the University of Texas at Austin. At the time, it sounded like science fiction. It is a solid reality today. As Canvas and Dall-E-2 tell you, “see for yourself”.
Jean-Claude Elias is a computer engineer and classically trained pianist and guitarist. He has regularly written computer articles, reviewed music albums and covered concerts for over 30 years.
Read more Opinion and analysis