Nvidia Canvas: AI for creating realistic landscape images

They are selling RTX's via Canvas.... no more no less.

It demonstrate that they feel that the software is better free to push their GPUs and this has a higher return than otherwise.

I'm quite lost on what you think would pay for this kind of software?

There is a large gap from tech demo to product, and it's even larger for AI products.

The average consumer is more willing to pay for hardware than software, even if all the value is created by the software.

It's the reason why Apple no longer charges for OS updates. Nvidia has essentially the same business model.

It's very hard to sell software to $averageconsumer unless that software is "free"

They have a monopoly on AI hardware, so it makes perfect sense for them to make people care about AI.

It’s fun to play with but most people really don’t have a reason to spend money on this kind of software.

When you look at GAN, I could see the data from this endeavor being used to improve it's output. I get it doesn't seem to have a direct application, but I would suspect that it actually is quite valuable to the media and entertainment space in the long run.

Right now, there is a whole bunch of architectures that are being discovered as being good for certain tasks.

At some point, there is going to be some sort of higher level research for ML in terms of generating an architecture for a particular task. And all this research is going to be used for this.

Probably an AI that could help us re watch our dreams?

tl;dr - It’s a GAN, they have some interesting limitations but can output 1024px images in real time on a consumer gpu.

The training labels may have been “segmentation maps”. These are regions of an image with a known scene description such as “cloud”, “trees”, “sky”. I’m not certain what model they use, but I bet it is a Stylegan2/3 modified to generate an image from a given set of segmentation masks.

Indeed, without the research context, it’s a little strange “why” you would want a product like this. Nvidia has done a lot of research to get GAN to run very fast on their RTX cards due to being mostly convolutional, operating directly in pixel (or wavelet) space rather than an embedding space. On my RTX 2070, I can run Stylegan2 at 1024px at a somewhat reasonable 10 FPS.

There is a real use case for this type of technology.

I'm the founder of https://ayvri.com, and we have a 3D virtual world where outdoor athletes watch their activities, and the activities of others.

As the resolution (and speed) of our 3D world improved, people got more interested and engaged with it.

I believe this is the future of video. Not volumetrically created through 20+ cameras, but with a single camera capturing the scene, and AI filling in the blanks based on what it knows.