jcjohns
Joined 12 years ago
Karma
95
Submissions
23
Member since
Nov 18
Recent submissions
Comment · 2 months ago
Comment · 2 months ago
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 and text prompt. Since Atlas makes camera pose explicit it can use posed input frames to shape the generated world, giving you a lot more creative control.
Another big differentiator is multimodality. Genie 3 only outputs pixels. Atlas also outputs pixels, but it can also output explicit 3D for the cases where you need it (such as plugging into game engines, simulators, or VFX workflows)
Comment · 2 months ago
Yes, as long as the input images are "poseable" -- if they were taken in the same space they need to have some overlap, where the same object or part of the scene is visible in multiple views so the pose can be predicted.
You can also manually position the input images in 3D space to create scenes generatively; we show examples of this in the "generating with spatial context" section
Comment · 2 months ago
It can operate in different modes for different applications.
If you only want to reconstruct the content in the input images without any imagination, Atlas can do sparse 3D reconstruction where it predicts a depth map for each input pixel, without predicting anything occluded or not visible in the input views. This could be used to implement your "fog of war" view.
But sometimes you want the model to stitch together views and imagine a coherent completion; this is a powerful tool for building and authoring generative worlds. For example the 1 minute video we show in the post was built by positioning seven unrelated input images in space and prompting the model to interpolate between them along a hand-specified camera path.
Comment · 2 months ago
Yes, one of the main goals of this model was to keep 3D consistency as the camera moves around; it can do this even without relying on an explicit 3D point cloud or Gaussian splat representation of the scene.
Comment · 2 months ago
Small correction, World Labs isn't betting exclusively on explicit 3D -- many of the Atlas results in this post are generated frames without any explicit underlying 3D representation. But Atlas can (optionally) output explicit 3D for the cases where you know you want it.
Comment · 2 months ago
It's an overloaded term that different people use for different things. At World Labs we think about three major categories of world models:
- Renderers output pixels or views of a world, either the real world or a generated world
- Simulators predict how the world responds to actions
- Planners predict actions for an agent to make to affect some change in the world
Under this taxonomy, Atlas is somewhere between renderer and simulator. It predicts high-quality views of a consistent 3D world (renderer) but it can also predict explicit 3D to aid in simulation. Atlas doesn't currently predict actions to directly drive a robot, so it isn't natively a planner; but its simulation abilities can help train another model to be planner.
Source: https://www.worldlabs.ai/blog/taxonomy-of-world-models
Comment · 2 months ago
In addition to frozen time, Atlas can handle some scene motion - see for example the candy New York City in the Camera-Controlled Generation section where cars are moving, or some subtle motion of the waves toward the end of the 1-minute video example.
But this is certainly one area we plan to improve going forward.
Comment · 2 months ago
I'm a cofounder at World Labs - happy to answer questions about Atlas!
Comment · 1 year ago
Make sure to try the live demo here:
Comment · 1 year ago
Arrow keys also work now, thanks for the feedback!
Comment · 1 year ago
That's weird, what device are you using?
(I'm part of World Labs)
Comment · 3 years ago
The usual narrative around this skill is that it was banned because it was too dangerous, but that doesn't ring true to me -- many release moves performed both by women on the uneven bars and men on the high bar have similar motions whose risk is surely equal to or greater than a Korbut flip.
For example, here's a Korbut flip: it's a back flip from the feet to catch the bar: https://youtu.be/NZYPcdj_wn4?t=15
Compare this with a Mo Salto, one of the hardest (legal!) release moves in the women's code of points: https://youtu.be/eIwTquLwGpA?t=26
On the men's side, the Korbut flip is a pretty similar motion to a Kovacs (https://www.youtube.com/shorts/6yRJaivL1TE) which is a staple of high-level men's gymnastics; in fact the basic Kovacs is "so easy" that you rarely see the vanilla version performed by top athletes! It's more common to do them with a full twist (Coleman/Cassina, e.g. https://youtu.be/8IeBXhijY0M?t=40) or in combination with other release moves (e.g. Zonderland at the 2012 Olympics https://youtu.be/I0TM2sOnvyI?t=1160). Hidetaka Miyachi is one of the few people to ever have competed a double-twisting Kovacs (both tucked and straight! https://youtu.be/RgW36EKyKyg?t=23), and there are a few videos online of people practicing a "double Kovacs" with an extra flip (e.g. https://www.youtube.com/shorts/zI8VEll7wKI) but nobody has ever done one in competition.
While it's perceived danger might have been a factor in the initial ban of the Korbut flip, in light of these modern release moves it's hard to see how that is still a good reason. Instead, I think the reason it remains banned is more aesthetic; bars are supposed to be a swinging event, and we don't want to allow skills that have athletes standing on the bar instead of swinging around it.
On the other hand, banning the Thomas salto (https://www.youtube.com/watch?v=vkQRWCsKyj0) and other similar roll-out moves on floor is very clearly motivated by safety -- these are indeed very dangerous, and athletes have been seriously injured by them (most famously Elena Mukhina who became a quadriplegic as a result of this skill).
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.