Come unwind with us after a long day of NeurIPS Conference, next Wednesday evening in Vancouver! lu.ma/worldlabsaiaft…

3D scene models are getting so good -- "futuristic office from a 1970s low budget science fiction film. Lots of nature in the office and view of a forest through a circular window. The inside of the office is cluttered with a bunch of strange looking gadgets. "

The future of immersive creation is here. World Labs image to 3D worlds: • Generate 3D worlds from a single image • Navigate scenes with real-time camera control • Use different effects without changing the scene I've had access and you can see some of my early results

"Tackling the problem of spatial intelligence is a fundamental and critical step towards full-scale intelligence" says Fei-Fei Li in an exclusive interview at #NeurIPS2024. Her startup, World Labs, aims to endow machines with 3D spatial intelligence. spectrum.ieee.org/fei-fei-li-wor…

Playing around with World Labs' 3D generator and combining it with Runway vid2vid to blend myself and the background better. Although it's only a side perspective, you can tell it doesn't have that static image feel because of how the 3D environment is moving.

More coming soon ! I manage to integrate for the first time volumetric 3D video made with Kartel.ai inside the AI world generated in gaussian splatting by World Labs !! I coded all in three.js! And it's possible to integrate elements on the fly ;) And so you can imagine soon

Had fun creating this cyberpunk video using World Labs for 3D scene generation and complex camera movements.

"Creativity requires controllability... This is why some of the current GenAI technology is deeply unsatisfying. Because it doesn’t give that controllability." —Dr. Fei-Fei Li, speaking at a16z speedrun last week

Experimented with World Labs ' 3D world generator and relighting by using Mickmumpitz's ComfyUI workflow.

I am really super happy to show you my research that transform 3D volumetric capture of man capture with Kartel.ai and with env gaussian splatting generated with World Labs in a three.js player . And all that is "upscale" using Hunyuan vid2vid model with a Lora train on

For “Neoghost” I just wanted to test out a pipeline using World Labs for environments, upres them with Magnific.ai, and then run the characters through ViggleAI.

JD Vance Josephine Teo Peter Kyle Clara Chappaz Erik Brynjolfsson Demis Hassabis Yann LeCun Also met up with an artist I’ve admired for a long time, and is now a dear friend of me and World Labs - Refik Anadol . We share the belief that AI can empower and augment human creativity if used right. 6/N

We're hiring! Please DM or apply directly via the link below!

Open Sourcing Forge: 3D Gaussian splat rendering for web developers! 3DGS has become a dominant paradigm for differentiable rendering, combining high visual quality and real-time rendering. However, support for splatting on the web still lags behind its adoption in AI.

Thought experiment: If you were blindfolded in a room and someone only described what’s around you… could you complete a task? Now imagine seeing the room. Instantly, your brain reconstructs the space in 3D. That’s why language isn’t enough. martin_casado and Fei-Fei Li

During the development of Spark, we built a demo to showcase the potential of using full scale AI generated 3D worlds as immersive VR environments.

Are you a badass genAI model optimization engineer? A fearless bizops rising star? A unicorn research engineer+TPM? An ambitious and experienced Product Engineer? Or believe you have a superpower to uniquely make a big impact to our mission World Labs, please check out these

Gaussian splats capture nuance and detail really hard to represent with traditional meshes ✨ These food scans are just 1-3 MB each and captured with a regular smartphone by tipatat No special equipment or setup. Rendered with Spark spark and Three.js. Link to demo the