We're quickly approaching HNFusion: Text-to-HN-Article-That-Implements-That-Idea ...
DreamFusion: Text-to-3D using 2D Diffusion
81–90 of 208 posts
Re: DreamFusion: Text-to-3D using 2D Diffusion
#82Cool.
The samples are lacking definition, but they're otherwise spatially stable across perspectives.
That's something that's been struggled with for years.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#83The most incredible thing here is that this demonstrates a level of 3D understanding that I didn't believe existed in 2D image models yet. All of the 3D information in the output was inferred from the training set, which is exclusively uncurated and unsorted 2D still images. No 3D models, no camera parameters, no depth maps. No information about picture content other than a text label (scraped from the web and often…
So I wonder if unusual angles that normally do not get photographed will be distorted? For example, underneath a table looking up.
They reapply noise to the potentially distorted image and then predict the de-noised version like the originally rendered first frame. So the image is at least internally consistent for the frame (to the extend the the system generates consistency whatsoever).
The example with a squirrel wearing a hoodie demonstrates an interesting edge case, the "front" of the squirrel (with hoodie over the head) show a normal hooded face as expected, but when you rotate to the "back" you get another face where the hoodie is low over the eyes. Each looks fine in isolation, but in aggregate it seems like we have a two-faced squirrel.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#84The most incredible thing here is that this demonstrates a level of 3D understanding that I didn't believe existed in 2D image models yet. All of the 3D information in the output was inferred from the training set, which is exclusively uncurated and unsorted 2D still images. No 3D models, no camera parameters, no depth maps. No information about picture content other than a text label (scraped from the web and often…
So I wonder if unusual angles that normally do not get photographed will be distorted? For example, underneath a table looking up.
It'll be delusions and guesses, rather than distortions.
It'll just make up some colours and geometries that don't contradict anything it already knows from the defined perspectives.
Or leave it empty.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#85Earlier quoted context omitted.
> This seems like basically plugging a couple of techniques together that already existed [...] In his Lex Fridman interview, John Carmack makes similar assertions about this prospect for AGI: That it will likely be the clever combination of existing primitives (plus maybe a couple novel new ones) that make the first AGI feasible in just a couple thousand lines of code.
That's a great example that reminds me of another one: there was nothing new about Bitcoin conceptually, it was all concepts we already had just in a new combination. IRC, Hashing, Proof of Work, Distributed Consensus, Difficulty algorithms, you name it. Aside from Base58 there wasn't much original other than the combination of those elements.
Base58 really should have been base57.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#86Is it a light version of script when the AGI comes fast
Re: DreamFusion: Text-to-3D using 2D Diffusion
#87Earlier quoted context omitted.
That's a great example that reminds me of another one: there was nothing new about Bitcoin conceptually, it was all concepts we already had just in a new combination. IRC, Hashing, Proof of Work, Distributed Consensus, Difficulty algorithms, you name it. Aside from Base58 there wasn't much original other than the combination of those elements.
Base58 really should have been base57.
Hello Stavros, I agree. When I look at the goals that base58 sought to achieve, (eliminating visually similar characters) I couldn't help but wonder why more characters were not eliminated. There is quite a bit of typeface androgyny when you consider case and face.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#88Did we hit some sort of technical inflection point in the last couple of weeks or is this just coincidence that all of these ML papers around high quality procedural generation are just dropping every other day?
My hot take is that we're merely catching up on until recently unutilized hardware improvements. There's nothing 'self-improving', it's largely "just" scaled up methods or new, clever applications of scaled up methods.
The pace at which methods scale up is currently a lot faster than hardware improvements, so unless these scaled up methods become incredibly lucrative (not impossible), I think it's quite likely we'll soon-ish (a couple years from now) see a slowdown.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#89Did we hit some sort of technical inflection point in the last couple of weeks or is this just coincidence that all of these ML papers around high quality procedural generation are just dropping every other day?
It has become clear since alphaGo that intelligence is an emergent property of neural networks. Since then the time and cost requirements to create a useful intelligence have been coming down. The big change was in August when Stable Diffusion was able to run on consumer hardware. Things were already accelerating before August, but that has really kicked up the speed because millions of people can play around with it and discover intelligence applications, especially in the latent space.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#90Earlier quoted context omitted.
Base58 really should have been base57.
Hello Stavros, I agree. When I look at the goals that base58 sought to achieve, (eliminating visually similar characters) I couldn't help but wonder why more characters were not eliminated. There is quite a bit of typeface androgyny when you consider case and face.
Yeah, I don't know why 1 was left in there, seems like a lost opportunity. Discarding l, I, 0, O, but then leaving 1? I wonder why.