WorldLabs' Atlas model turns one or more photos into a navigable 3D environment you can explore in real time. It reconstructs geometry and texture from a single image, and can fuse up to seven photos into one scene. Compared to other techniques, it needs far fewer images to get the same quality.
One of the cooler things I saw this week, the new Atlas model out of WorldLabs. This is really cool because you give it an input image and you tell it a camera path and it will generate an output based on that. This isn't just generating a video like this isn't a video generator. This is generating like an environment. We could see the input image that was given and then it sort of reconstructs everything based on that one image. Here's another example where it took this one image and I can actually— I'm manipulating this in real time as I move my mouse around, look at different angles From just that single image. And if you give it 2 images, you can see that it can combine those 2 images into a single scene that you can move around and manipulate. This one here looks like it's got 1, 2, 3, 4, 5, 6, 7 different inputs to generate this output here. I can imagine, you know, going and taking a whole bunch of pictures inside of your house, putting them into a platform like this, and easily remapping the house. Now, I know you could already do that with things like Gaussian Splats, but this does it with a lot less photos, it seems.
AI News: Dots, GPT-6.1 Sol, Sonnet 5.5, Gemini 4, and everything you need to know
