Here's a quick video of Wooorld (𝗪𝗼𝗼𝗼𝗿𝗹𝗱) with @Oculus Passthrough recorded on an Oculus Quest. We will have a lot more to share soon. More info at wooorld.io Follow me and 𝗪𝗼𝗼𝗼𝗿𝗹𝗱 and help us spread the word with likes & RTs! 🙏

Who else hates when this happens? #metaverse #VR #VirtualReality #truestory

😮

Google's New Model for Automatic 3D Creature Creation 80.lv/articles/googl…

Progress is sometimes just getting a different error than the one you've been getting for the last 30 minutes.

Incredibly excited to share some images of the recently released device #MagicLeap2. Stoked to be part of this pivotal moment at Magic Leap, that is shaping the future of #augmentedreality. #technews #healthtech #metaverse

We are hiring - recommendations and signal boosts are much appreciated!

😲 def playing with this over the weekend

Incredible

Passthrough is really nice, but it'd be a lot nicer if it had some colors. It's a good thing that my #iPadPro can help with that. #OculusQuest2 #MadeWithUnity

I brought my childhood imaginary friend back to life using A.I. (#GPT3) and it was one of the scariest and most transformative experiences of my life. A thread 🤖 (1/23)

This is how the real Metaverse will happen. The web has evolved to be the most powerful computing platform in the world. It is not just the natural choice for enabling the Metaverse, it is guaranteed that it will become the de facto winner. Why?

Introducing the Luma✨Unreal Engine alpha! Fully volumetric Luma NeRFs running realtime on Windows in UE 5 for incredible cinematic shots and experiences, starting today! Try now: lumalabs.ai/ue

I was just playing around with the Snap AR #AI Machine Learning 'eraser' filter, combining it with regular LensStudio effects But then I discovered that I accidentally created a "live #Banksy generator" #Snapchat lens! Give it a try here: lens.snapchat.com/320f9f1726a049…

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: huggingface.co/papers/2308.04… Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires

This enables a number of exciting applications such as the composition of different dynamic scene elements, first-person view synthesis and temporally consistent 4D scene editing. It’s also FAST! These render at 850 FPS, and only take around 2 hours to train on a single GPU.

If you find dynamic NeRFs cool, check out this work where we exploit some of the very interesting properties of the 3D Gaussian Splatting for persistent tracking through time. We learned a lot working with Jonathon Luiten that helped us understand better the power of 3DGS.