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…
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…
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…
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…
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.
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…
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…
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…
I'm a cofounder at World Labs - happy to answer questions about Atlas!
Make sure to try the live demo here: https://rtfm.worldlabs.ai/
Arrow keys also work now, thanks for the feedback!
That's weird, what device are you using? (I'm part of World Labs)
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…
This makes sense in theory, but is hard to get working in practice. We tried using nvjpeg to do JPEG decoding on GPU as a additional baseline, but using it as a drop-in replacement to a standard training pipeline gives…
I'm one of the authors of this CVPR paper -- cool to see our work mentioned on HN! The Uber paper from 2018 is one that has been floating around in the back of my head for a while. Decoding DCT to RGB is essentially an…
I don't think Google has ever released models trained on JFT. But if you're interested in large-scale vision models, you can check out these models from Facebook trained on 940M Instagram images (several times bigger…
Yes, I think that is a likely explanation. Also note that Vincent Dumoulin is an author of both the deconv-checkerboard blog post and the new paper from Google, and that the new Google paper uses the…
Real-time neural style transfer is not new; in the past year there have been several academic papers [1-4] on this topic and several open-source code releases: https://github.com/jcjohnson/fast-neural-style…
Author here. I'm not a lawyer so I can't write anything too official myself, and after some searching it seemed like none of the standard open-source licenses apply to this use-case.
Code is here: https://github.com/jcjohnson/densecap
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…
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…
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…
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…
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.
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…
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…
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…
I'm a cofounder at World Labs - happy to answer questions about Atlas!
Make sure to try the live demo here: https://rtfm.worldlabs.ai/
Arrow keys also work now, thanks for the feedback!
That's weird, what device are you using? (I'm part of World Labs)
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…
This makes sense in theory, but is hard to get working in practice. We tried using nvjpeg to do JPEG decoding on GPU as a additional baseline, but using it as a drop-in replacement to a standard training pipeline gives…
I'm one of the authors of this CVPR paper -- cool to see our work mentioned on HN! The Uber paper from 2018 is one that has been floating around in the back of my head for a while. Decoding DCT to RGB is essentially an…
I don't think Google has ever released models trained on JFT. But if you're interested in large-scale vision models, you can check out these models from Facebook trained on 940M Instagram images (several times bigger…
Yes, I think that is a likely explanation. Also note that Vincent Dumoulin is an author of both the deconv-checkerboard blog post and the new paper from Google, and that the new Google paper uses the…
Real-time neural style transfer is not new; in the past year there have been several academic papers [1-4] on this topic and several open-source code releases: https://github.com/jcjohnson/fast-neural-style…
Author here. I'm not a lawyer so I can't write anything too official myself, and after some searching it seemed like none of the standard open-source licenses apply to this use-case.
Code is here: https://github.com/jcjohnson/densecap