Futurists have been predicting when we'll have stable fusion for decades, but now we suddenly got stable diffusion working. That's good too, not what we wanted, but good. We're gonna need stable fusion or other renewables to run stable diffusion though. /s
DreamFusion: Text-to-3D using 2D Diffusion
141–150 of 208 posts
Re: DreamFusion: Text-to-3D using 2D Diffusion
#142Can someone explain what's going on in this example from the gallery? The prompt is "a humanoid robot using a rolling pin to roll out dough": https://dreamfusion-cdn.ajayj.com/gallery_sept28/crf20/a_DSL... But if you look closely, the pin looks like it's actually rolling across the dough as the camera orbits.
I think what's happening here is that the flat-looking table is actually raised up in the center, in the shape of something like a smooth pyramid. There's dough painted on both sides of the rolling pin, but because of the curvature of the "table" you only see each side's dough when the camera is on that side of the pyramid.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#143Earlier 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…
> Our eyes only ever see 2D images and we learn 3D structure from that I think that would be an oversimplification. We do have some 3D information from focus and eye convergence.
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.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#144Earlier quoted context omitted.
From the abstract: “We introduce a loss based on probability density distillation that enables the use of a 2D diffusion model as a prior for optimization of a parametric image generator. Using this loss in a DeepDream-like procedure, we optimize a randomly-initialized 3D model (a Neural Radiance Field, or NeRF) via gradient descent such that its 2D renderings from random angles achieve a low loss.” This seems like b…
> This seems like basically plugging a couple of techniques together that already existed as with a majority of ML research
> This seems like basically plugging a couple of techniques together that already existed
Do this enough times and eventually the thing you have looks indistinguishable from something completely novel.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#145Fun that they had an octopus playing a piano.
I made the same thing the old fashioned way. Mine can actually play though. https://twitter.com/LeapJosh/status/1423052486760411136 :P
Re: DreamFusion: Text-to-3D using 2D Diffusion
#146What 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 story? That yes, the mimicry is All sentience actually is. Nothing more.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#147As someone who went to college for 3D animation in +* 1997* + AND DESIGNED the datacenter for luca' presidio complex.. where-by learning that Pixar was developed by steve jobs when lucas didnt think there was a future for computer animation... and so steve bought the death star from lucas... That became pixar... AI is going to fucking kill it - what will happen in the next decade will be ANYONE uploading a script to…
It's going to be worse then that. I'll just write a summary and an AI will generate the full script. Then the movie will be generated from the script. The full source code and assets for a video game too.
All the primitive components for this future seem to be at an early stage of inception. We can't say for sure whether they will mature to the point where they can replace us, but the trajectory is certainly pointing in that direction.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#148Earlier quoted context omitted.
Maybe deadline for neurips which is coming up?
This was submitted to ICLR
Whose full paper submission deadline was also 2 days ago.
This should be further up than all the speculation about AI accelerationism. There's a very simple explanation why a lot of awesome papers come out right now, it's prestigious conference paper deadlines.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#149Fun that they had an octopus playing a piano. I made the same thing the old fashioned way. Mine can actually play though. https://twitter.com/LeapJosh/status/1423052486760411136 :P
Text to 3D animation is the obvious next step though.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#150No post body was provided.