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

Atlas: A World Model for Spatial Intelligence

worldlabs.ai

Post reply on HN
Print view View original

41–50 of 64 posts

Re: Atlas: A World Model for Spatial Intelligence

#41

Post by dmarcos »

xyzsparetimexyz wrote: post #33
dmarcos wrote: post #11

Earlier quoted context omitted.

I believe so. This is not a model that generates pixels frame by frame from user input like genie 3. Instead, there’s an actual 3D scene / structure generated (point cloud, 3dgs) from the input images.

Wrong, it does go straight to generating images.

From blog post:

“It generates both image frames from novel views and explicit 3D outputs”

Model can indeed generate novel views but I don’t think in real time (I could be wrong). If you want to navigate a space in real time as user above was asking gotta rely on the 3D output and the explicit representation will provide continuity. User likely was referring to the limitations we’ve seen on video-style world models like genie and precursors.

Re: Atlas: A World Model for Spatial Intelligence

#42

Post by jcjohns »

hi_hi wrote: post #30
jcjohns wrote: post #12

I'm a cofounder at World Labs - happy to answer questions about Atlas!

How long does it take to process from input images to model output?

Unfortunately that's a complex question... this depends on the number of diffusion steps, the size of the context, the image resolution, and the type and number of inference devices we use. There are lots of knobs to trade off speed, quality, latency, throughput, and cost.

An ideal workflow would be something semi-interactive that you can use to quickly iterate on an idea, followed by a longer offline bake-out to generate final production-quality assets.

Re: Atlas: A World Model for Spatial Intelligence

#45

Post by lurker137 »

jcjohns wrote: post #40
lurker137 wrote: post #29

Earlier quoted context omitted.

How does it compare to Google's Genie 3 or other similar models? At first glance it does look much more impressive visually

One of the biggest differences is the conditioning signal. Genie 3 and similar input raw keyboard commands (WASD + arrow keys), while Atlas inputs camera poses. This small difference means that Genie 3 has no 3D whatsoever; the model needs to learn an internal mapping between keyboard commands, world states, and pixels; and with Genie 3 there is no clear way to control the generated world aside from the input image a…

Thanks, those are great points, now I'm definitely excited for the full release to try it out

Re: Atlas: A World Model for Spatial Intelligence

#47

Post by kkotak »

jcjohns wrote: post #12

I'm a cofounder at World Labs - happy to answer questions about Atlas!

Maybe a dumb question, but when navigating the worlds on the site, I notice that the space is 3D, but the objects (the drum set, or the vending machine) are flat 2D layers that one cannot walk around or examine from a different angle. Is this the inherit limitation of the approach or future features? Thanks.

Re: Atlas: A World Model for Spatial Intelligence

#48

Post by chriswen »

teraflop wrote: post #28

The blog post doesn't seem to mention what strikes me as the most interesting application of a model like this, namely extracting semantic information from its latent space. It mentions robotics applications, but only in the context of generating realistic world models for simulation. If you have a robot deployed in an environment, generating synthetic views of the environment you're in doesn't have any obvious value…

Sounds like something Atlas probably is a great base model for.

Re: Atlas: A World Model for Spatial Intelligence

#49

Post by chriswen »

soundworlds wrote: post #32
Vakaiser wrote: post #26

This is incredible. One potential application that I'm thinking about already is the rapid iteration of video-game map blocking. Being able to drop in some 'initial state' configuration and then have it procedurally generate a handful of alternative configurations could make rapid prototyping a significantly quicker experience, especially if you wanted to see what a potential end result could look like. Furthermore,…

Yeah where I've been previously skeptical for using AI in creative ways, basically when these tools get to the point where you have a tight iteration loop, it enables a great creative flow. You still need the technical proficiency to be able to make edits beyond that, but I think studios would be foolish to let go of their experts in the first place.

Atlas will complement Marble, our current product that can be used for applications like this nicely :) These are indeed great applications for the model. Atlas gives us unprecedented levels of control as well as generative capabilities and is 3d consistent.
Post reply on HN