Ever dreamt of having a job where you deliver mail to the residents of a tiny planet? Us too. messenger.abeto.co #webgl #threejs

@NVIDIAAI recently released InstantSplat which allows for fast 3D reconstruction, so I decided I wanted to make a demo of it using @rerundotio and @Gradio! It's one of the fastest ways to go from sparse images -> Gaussian splat I've come across. pablovela5620-instant-splat.…

We will be able to turn regular 2D videos into volumetric 4D content sooner than you expect.

Metas iPhone moment

Building a drag-and-drop editor for creating @discord games and Activities, all within Discord. Yes, right inside Discord 😱 Think of it as a mix between Webflow and Roblox, to create games and community experiences on Discord. @JoshLu @AnjneyMidha

Today we'd like to humbly share some thoughts about an **important but often-overlooked** feature of UI in XR -- UI Mobility 💡 in this thread #CHI2024

Here’s an early preview of ElevenLabs Music. All of the songs in this thread were generated from a single text prompt with no edits. Title: It Started to Sing Style: “Pop pop-rock, country, top charts song.”

"Every pixel will be generated (not rendered)" - J. Huang The TV shows, movies, ads, video games and more. We're getting there 👇👇

I’m here at Laval Virtual demoing @Luminous_XR mixed reality applications at the Meta booth. Come swing by if you’re attending!

AI rendering in game dev is inevitable. Anyone working in this space?

Job Simulator is one of the highest selling VR games of all time and its technical lead has a message for developers: You need to have a hand tracking plan now: uploadvr.com/editorial-hand-…

Google just revealed an ABSOLUTE depth estimation model 🤯 As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️

Oh god why would you showcase the power of mixed reality using a 2D image.

This scene was scanned using only 3 pictures 🤯 In my opinion, this was the biggest flaw of NeRFs & 3D Gaussian splats: they are trained from scratch every time with no knowledge of the world. With ReconFusion, we now acquire it from diffusion models More examples below ⬇️⬇️

the older i get, the more i'm convinced the single most important trait that matters in your friends, coworkers, life partner, and kids - is high agency.

a lot of people can't believe this is an AR render. here's a side by side of a more difficult scene - this time with real time lighting, shadows, and diffraction through simulated amber:

Excited to present our new paper "LucidDreamer", a new #3D #gaussiansplatting scene generation pipeline! LucidDreamer can generate high-quality 3D gaussian splatting scenes from any text or image prompt. Project page 👉: luciddreamer-cvlab.github.io… Paper 📃: huggingface.co/papers/2311.1…

People are just starting to realize the power of Local LLMs Especially with new Apple chips. It's a game-changer Let me show you: Falcon is 180B LLM. It is the size of GPT3. How fast would it run on your Mac? Apple M3 Max: 3.5 tokens/sec We can compare it to 2 x A100 (2 x 30k$) 2x A100 80GB: 7 tokens/sec Now add to this the recent speed of @NousResearch & @teknium with models like openHermes And the fact that soon they will add Vision functionality to send images x.com/Teknium1/status/172661… and we get real competition to commercial models from OpenAI and Anthropic More of independent companies start to publish their model weights Take 01.ai team from China. It is currently leading the OSS leaderboard in quality & context size 01 team has 200k context window model. It's the 7 copies of Shakespeare's Hamlet which can fit onto a single prompt GPT4 turbo has only 128K 7B models like Mistral are already running at 40 tok/s! This is insanely fast! I have run a test on my old M1 a gif below to give you a feeling of the speed of it. Absolutely stunning work is done by @ggerganov. Georgi & llama.cpp community have literally shaped the progress of open source models with llama.cpp project. It allows you to run any LLM on your computer. You can even run llama on your ios with it I am incredibly bullish on Apple metal & local computations. There are many interesting projects rising around it, one that came to my mind is @opentensor – decentralized commodity of computing resources like selling your GPU to someone And I haven't even started on the power of webGPU & Web LLM What other interesting stuff have you seen? share in comments

Build for visionOS with Unity Pro, Enterprise and Industry license starting today! We're opening up the closed beta for PolySpatial and visionOS support letting unity developers build for Apple Vision Pro! I can't wait to see what you build! More info: create.unity.com/spatial

This is huge!! Spline now supports Gaussian splats 👀 You can now capture anything in 3D from your phone with Luma, export the .ply file, import it into spline, crop, adjust, and embed on your site. Luma Spline Webflow is an insane 3D workflow 🔥