Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DreamFusion: Text-to-3D using 2D Diffusion

dreamfusion3d.github.io

Post reply on HN
Print view View original

181–190 of 208 posts

Re: DreamFusion: Text-to-3D using 2D Diffusion

#181

Post by cornel_io »

sandgiant wrote: post #160
modeless wrote: post #127

Earlier quoted context omitted.

The model clearly has an understanding of the 3D structure of objects. If it didn't, using it to generate 3D models wouldn't work. The knowledge that the leg bone is connected to the knee bone, etc, isn't coming from NeRF, it's all in the "2D" model. Sure, maybe you could distill that knowledge into a different model architecture that is somehow natively 3D in order to improve the efficiency of sampling. But that's m…

I think this is a misunderstanding of how these models work. The model does not understand anything at all. It's computing correlations. I could spend all day computing correlation without ever understanding what the correlations correspond to in the physical world. The correlations could still amount to a useful description of some physical phenomenon, but their interpretation requires much more than just the abilit…

Your brain merely computes correlations. Does that make it any less intelligent?

At some point we have to accept that when you layer simple ops on top of simple ops enough times you get complex behavior.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#182

Post by icoder »

machina_ex_deus wrote: post #177
beambot wrote: post #57

Earlier 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.

Billions of creatures with stronger neutral networks, more parameters, better input have lived on earth for millions of years, but only now something like humans showed up. I fully expect AI to do everything animals can do pretty soon, but since whatever it is that differentiates humans didn't happen for million of years, there's good chance AGI research will get stuck at a similar point.

Nature has the advantage of self organisation and (partially because of that) parallelism, that's proved hard to mimic in man made devices. But on the other hand, nature also has obstacles such as energy consumption, procreation & development, and survival, that AI doesn't have to worry about.

I think finding a niche for humans has proved difficult especially because of those reasons, and AI can take those hurdles much easier.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#183

Post by deltasevennine »

F2hP18Foam wrote: post #166
deltasevennine wrote: post #143

Earlier quoted context omitted.

its not an over simplification. The extra information from convergence is negligible... our eyes derive virtually identical information when looking at flat 2D pictures of 3D scenes. Evidence of this is everywhere in pictures.

I'm sure people born with one eye are perfectly able to understand the concept of 3D

Dunno if you fully read my comment. But we're in agreement.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#184

Post by danielbln »

rjmunro wrote: post #176
drKarl wrote: post #40

Earlier quoted context omitted.

Why the downvote? I wasn't being sarcastic, it was a honest question, I'm really impressed how far this technology has come since GPT-3 2 years ago to DALl-E and Stable Diffusion ro Meta's text to video to this...

Maybe because you said "Metaverse" (and to some extent "VR") making it sound like sci-fi nonsense. You could have just said: How long then until we get photorealistic AI generated 3D games and experiences?

You probably want to use ML instead of AI then.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#185

Post by cuuupid »

LarsDu88 wrote: post #156
cuuupid wrote: post #74

Earlier quoted context omitted.

A large portion of the ML community (rightly) discredits Google papers because: - they rarely provide the data or code used so it's basically "i swear it works bro" research - what they achieve is usually through having the most pristine dataset on the planet and is often unusable by other researchers - other times they publish papers that are basically "we slightly modified this excellent open source paper, slapped…

IMO the biggest algorithmic advances made by Google such as the transformer have greatly pushed the field forward. The giant model's that will have similar variations released in the next 3 months actually aren't that important on a conceptual level except as a PoC.

While the transformer model is important that was 1 paper in an ocean they put out every year.

Also it’s one of the only papers they put out that falls completely outside what I put above. They released everything about it including the model code, pretrained weights, the techniques; and it took quite a while for the model to “catch on” while it was peer reviewed and reproduced by others.

Something something broken clock

Re: DreamFusion: Text-to-3D using 2D Diffusion

#186

Post by Workaccount2 »

throwaway675309 wrote: post #56
achr2 wrote: post #51

The thing that frightens me is that we are rapidly reaching broad humanity disrupting ML technologies without any of the social or societal frameworks to cope with it.

I'm usually not a fan of this general hand wringing / fear mongering around ML that a lot of people with too much time and not enough STEM background constantly bring up. Stable diffusion has been made available to the public for quite a while now and if anything has disproved a lot of the ungrounded nonsense that made companies like OpenAI censor their generative models.

SD has been out for about a month and it is first gen technology. If "quite a while" was 5 years, then sure, I'll agree.

But we are one month into the experiment, and the technology still struggles to get wholly authentic looking media. I'd say it would be wise to give it a few years before claiming victory.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#187

Post by mattnewport »

deltasevennine wrote: post #146

What does this mean for our understanding of intelligence? It trivializes it, in my opinion. When asked the question of is lambda/GPT-3 and/or DreamFusion and it's derivatives an aspect of sentience? there's always a bunch of people who are repeating the same cliche negative line, of "no, it's only attempting to statistically mimic sentience." I agree with the reasoning. But have we considered the other side of the s…

AI is getting quite good at a lot of things humans consider fairly difficult (like this example) but has made less progress at things humans consider fairly easy (e.g. maintaining consistency across paragraphs of text for GPT3, navigating 3D space, learning from small numbers of examples). That suggests that there is still a gap between what current AI approaches are doing and what the human brain is doing that doesn't just come down to throwing ever more data at the problem.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#188

Post by deltasevennine »

mattnewport wrote: post #187
deltasevennine wrote: post #146

What does this mean for our understanding of intelligence? It trivializes it, in my opinion. When asked the question of is lambda/GPT-3 and/or DreamFusion and it's derivatives an aspect of sentience? there's always a bunch of people who are repeating the same cliche negative line, of "no, it's only attempting to statistically mimic sentience." I agree with the reasoning. But have we considered the other side of the s…

AI is getting quite good at a lot of things humans consider fairly difficult (like this example) but has made less progress at things humans consider fairly easy (e.g. maintaining consistency across paragraphs of text for GPT3, navigating 3D space, learning from small numbers of examples). That suggests that there is still a gap between what current AI approaches are doing and what the human brain is doing that doesn…

You just picked an arbitrary gap though. And it seems like a small gap that's crossable.

For example just 2 weeks ago there were two other gaps that you could've used in your example. You could've said 3D interpretation of images wasn't possible and the creation of animated movies wasn't possible and you could've said these few things suggest that there's a gap in what the human brain is doing and what the AI is doing and just throwing more data at the problem doesn't fix it.

Those two examples would be irrelevant today as both of those gaps have Effectively been crossed.

See what I'm saying here. There's two ways of looking at it even from your perspective... Either that gap is so large that the human brain is completely different. Or the gap is small, trivial and will be crossed very very soon.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#189

Post by deltasevennine »

mattnewport wrote: post #187
deltasevennine wrote: post #146

What does this mean for our understanding of intelligence? It trivializes it, in my opinion. When asked the question of is lambda/GPT-3 and/or DreamFusion and it's derivatives an aspect of sentience? there's always a bunch of people who are repeating the same cliche negative line, of "no, it's only attempting to statistically mimic sentience." I agree with the reasoning. But have we considered the other side of the s…

AI is getting quite good at a lot of things humans consider fairly difficult (like this example) but has made less progress at things humans consider fairly easy (e.g. maintaining consistency across paragraphs of text for GPT3, navigating 3D space, learning from small numbers of examples). That suggests that there is still a gap between what current AI approaches are doing and what the human brain is doing that doesn…

Every one of these AI improvements from DreamFusion to Metas introduction moves the needle closer and closer.

If someone asked this question when GPT-3 came out there'd be thousands of negative retorts throwing out the same tired lines. Now this statement is getting harder and harder to refute.

Re: DreamFusion: Text-to-3D using 2D Diffusion

#190

Post by mattnewport »

deltasevennine wrote: post #188
mattnewport wrote: post #187

Earlier quoted context omitted.

AI is getting quite good at a lot of things humans consider fairly difficult (like this example) but has made less progress at things humans consider fairly easy (e.g. maintaining consistency across paragraphs of text for GPT3, navigating 3D space, learning from small numbers of examples). That suggests that there is still a gap between what current AI approaches are doing and what the human brain is doing that doesn…

You just picked an arbitrary gap though. And it seems like a small gap that's crossable. For example just 2 weeks ago there were two other gaps that you could've used in your example. You could've said 3D interpretation of images wasn't possible and the creation of animated movies wasn't possible and you could've said these few things suggest that there's a gap in what the human brain is doing and what the AI is doin…

I'm saying something different, that the most impressive examples of AI breakthroughs are doing things that humans find hard / are bad at. Meanwhile there are many things that people find easy / do without thinking / can be done by dogs or very young children that AI struggles with.

It suggests to me that what most current approaches are doing is something fairly different from what human / animal intelligence is doing in important ways. That means we will likely continue to see AI do increasingly amazing things while at the same time struggling to perform a lot of tasks that are quite basic for humans.

It is the fact that AI is proving to be a better artist than most humans while not being able to do many things that are simple for a 4 year old that suggests strongly to me that some of the fundamental mechanisms are fairly different still, or current AI approaches are missing some key insights.

I could be wrong. I'd bet money that I'm right if there was an easy way to do it though.

Post reply on HN