danybittel

The bumblebee was my first attempt, the tracking didn't quite work, so you get ghosting. Others too have ghosting, usually happens when part of the insect moves, while shooting (which takes 4h). They dry and crumble after a while.

That would be awesome if it worked, from a curious look I can't say why not. I'll have to investigate a bit more. Thanks for bringing it up.

Thanks for pointing that out, fixed it.

Thanks for the links, that is great to know. I'm not quite sold if it's the better approach. You'd need to do SfM (tracking) on the out of focus images, which with macro subject can be really blurry, I don't know how well that works.. and a lot more of images too. You'd have group them somehow or preprocess.. then you're back to focus stacking first :-)

Nothing fancy. Postshot does need a nvidia card though, I have a 3060Ti. A single insect, with around 5 million splats takes about 3 hours to train in high quality.

This sound intriguing. Is the camera placed above the scene? How do those interactive Dance Floors come into play, did you use them for the light? Do they not have triggers, when somebody stands on it?

I've seen the sand table installation before, pretty cool. I was interested in how they did the fluid in particular. Thanks anyway.

Ha, I've thought about adding a small fan too. Definitely need to do that.

Do you have a picture of the installation at the science museum?

The color just rotates through the oklab space (change hue only).

I know and like Brett Victor's work. Definitely a source of inspiration!

That would be hard to source / use, as It's a bit dated. But the technic behind it could be replicated. It uses IR LED on the bezel, around a glass. With total internal reflection the light only shows up where you touch the glass. Then film that with a camera. The advantage to my method, you don't get interference of objects hovering above the screen. But getting the camera & display behind the screen, could be hard.

I would love to have this on a transparent TV.

Like a regular 2D fluid sim, the projection is not the bottleneck. The sim can be slow or fast depending on the quality you want. This one runs fine on integrated graphics card on my laptop.

Thanks! That is the plan.. I created the demo to pitch to interested people.

I just finished create my first gaussian splat of a macro: https://superspl.at/view?id=cf6ac78e

Isn't "fund people" just hiring without the extra steps?

It should be, it is part of 1.2. (https://vulkan.gpuinfo.org/listfeaturescore12.php the first entry bufferDeviceAddress, supported by 97.89%)

Or did you mean some specific feature? I haven't used it on mobile.

> Unfortunately, Shader programs are currently restricted to the Logical model, which disallows all of this.

That is not entirely true, you can use phyiscal pointers with the "Buffer device address" feature. (https://docs.vulkan.org/samples/latest/samples/extensions/bu...) It was an extension, but now part of Vulkan. It is widely available on most GPUS.

This only works in buffers though. Not for images or local arrays.

You might want to consider using words (16 bit integer) instead of halfs? Then you can use all the 65k value precision in a range you choose (by remapping 32bit floats to words), potentially adjust it every frame, or with a delay.

If you say 1 pass bucket sorting.. I assume you do sort the buckets as well?

I've implemented a radix sort on GPU to sort the splats (every frame).. and I'm not quite happy with performance yet. A radix sort (+ prefix scan) is quite involved with lot's of dedicated hierarchical compute shaders.. I might have to get back to tune it.

I might switch to float16s as well, I'm a bit hesitant, as 1 million+ splats, may exceed the precision of halfs.

How do you do the rendering? Is it sorted (radix?) instances? Do you amortize the sorting over a couple frames? Or use some bin sorting? Are you happy with the performance?

Pretty sure that's illegal in Europe, if she were an AI.

Error diffusion dithering is kind of old fashioned. It is a great algorithm where you only need to go though the image once, pixel by pixel. But it doesn't work well with todays hardware, especially GPUs. Would be fun to come up with new algorithms that are better parallelizable.

What you're looking for is https://en.wikipedia.org/wiki/Superoptimization.

f or g may have side effects too. Like writing to memory. Now a conditional has a different meaning.

You could also have some fun stuff, where f and g return a boolean, because thanks to short circuit evaluation && || are actually also conditionals in disguise.

YAGNI: You aren't gonna need it.

“Perfection is achieved not when there is nothing left to add, but when there is nothing left to take away”

“Less is more”

“The value of a creative product doesn’t lie in how much is there, but in how much has been discarded.”

rttm: Reduce to the max

"Kill your darlings"

...

This is absolutely not what I'm seeing. Travel is at an all time high with crazy amount of traffic jams, every weekend. Restaurants are full, parks, museums.. full. It is almost eerie just how everybody is going out and about like there is no tomorrow. I reduced my friend circle willingly, otherwise they would keep nagging me about doing stuff together, but I currently want to spend time on my own projects.

But we eat more. People often seem to not realize that overweight is a risk factor for cancer.

You are probably joking, but that is literally what MS said, they don't even hide it. A quote from the register: "Suleyman (Head of MS AI) did allow that there's another category of content, the stuff published by companies with lawyers." (https://www.theregister.com/2024/06/28/microsoft_ceo_ai/)

"I think that with respect to content that is already on the open web, the social contract of that content since the 1990s has been it is fair use"

And that social contract did not include AI. You put content on the internet because you had certain expectations on how it'll be seen or used.