Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Experimenting with environment styles in my off-axis projection demo. These are Gaussian splats rendered in the browser, switching via keyboard. -> Blender basic layout -> World Labs (chisel) -> three.js / Spark 2.0 -> Mediapipe (face-tracking)

88,044 Aufrufe • vor 6 Monaten •via X (Twitter)

41 Kommentare

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

Here is basic blender scene I modeled before taking it into @theworldlabs as structured input

Profilbild von Christian Stewart
Christian Stewartvor 6 Monaten

This is so awesome, I remember the Johnny Lee wiimote tracking demo like it was yesterday, I set that thing up as a kid and played with it for hours and hours. Would love to check out a repo with what you've done here.

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

Yes a minimal repo here!

Profilbild von robot 2.0
robot 2.0vor 6 Monaten

he does it again

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

🫡🫡🫡 trying my best

Profilbild von Tom Matlock
Tom Matlockvor 6 Monaten

It's honestly magic what's possible

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

🫡🪄

Profilbild von Kint Sugi
Kint Sugivor 6 Monaten

Please tell me you filed for a provisional patent? This is the coolest shit I've seen since 3D gaming. Someone's going to give you a billion dollars for this.

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

🙏🥹

Profilbild von Kint Sugi
Kint Sugivor 6 Monaten

Seriously though. It was $75 when i did it, gives you Patent Pending status for 12mo. Just make sure you submit the full patent within 12mo or it becomes public domain. This tech is going to be huge, bro! It's like 3D glasses but without the glasses.

Profilbild von ⛉⚔ ᵂⁱᴿᵉᴰ•ᵁˢᴰ ⚔⛊ 🧶
⛉⚔ ᵂⁱᴿᵉᴰ•ᵁˢᴰ ⚔⛊ 🧶vor 6 Monaten

@CorridorDigital, could you please do an episode on this? 🙏 It looks interesting.

Profilbild von Supernal
Supernalvor 6 Monaten

dude wtf

Profilbild von 𝘈 𝘒 𝘈 𝘚 𝘏
𝘈 𝘒 𝘈 𝘚 𝘏vor 6 Monaten

The accelerometer APIs could also help with aligning the viewport for an inside out tracking thingy

Profilbild von Quan Stewart
Quan Stewartvor 6 Monaten

This is cool.

Profilbild von nat'
nat'vor 6 Monaten

howw

Profilbild von Enough Already
Enough Alreadyvor 6 Monaten

These are awesome; would be great to see how it feels in a game environment which is tuned for multi-dimensional gameplay.

Profilbild von Marlon Fuentes ⚡️
Marlon Fuentes ⚡️vor 6 Monaten

There’s a world model hackathon in nyc this weekend and I would love to try this!

Profilbild von DeRon Rashad | SIGTREX
DeRon Rashad | SIGTREXvor 6 Monaten

This is so dope‼️

Profilbild von hu go 🫡
hu go 🫡vor 6 Monaten

this is absolutely amazing

Profilbild von Spiegs
Spiegsvor 6 Monaten

@alightinastorm Wtffffff this is so cool

Profilbild von muralist1
muralist1vor 6 Monaten

Super cool

Profilbild von Professor Pixel
Professor Pixelvor 6 Monaten

This is very cool.

Profilbild von ienex
ienexvor 6 Monaten

very smart use of face/eye tracking!

Profilbild von iliesaya
iliesayavor 6 Monaten

can we try a live demo somewhere ?

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

I have a basic demo here with main logic. I don’t have this current one up

Profilbild von kalin
kalinvor 6 Monaten

how many splat quads for this level of detail?

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

Each GS is about 500k splats (optimized this a bit form the 1 million) then using to render them via three.js

Profilbild von ✨ OHMplex 🚀(Olaf Ohm)
✨ OHMplex 🚀(Olaf Ohm)vor 6 Monaten

Check out the game MOSS and MOSS 2 and think about, what is possible 😅

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

@the_OPX yes! One of my first and still favorite VR games I've every played. So well done

Profilbild von Oksowhat
Oksowhatvor 6 Monaten

If you place a separate 3d object in the scene, could it be included with face tracking? Like I'm thinking minimal 3d interactive game. This is awesome. Keep up these nexgen ideas coming Ian

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

Yes! 100% also planned to have a character move around!

Profilbild von TARartRAT
TARartRATvor 6 Monaten

i don't even understand what i am looking at.

Profilbild von Michael
Michaelvor 6 Monaten

@threejs Wow this is truly mind-blowing. This is how I imagined Zoom and Google Meet's background should work

Profilbild von Magdalena Djordjevic
Magdalena Djordjevicvor 6 Monaten

Great work 👏

Profilbild von O₿1
O₿1vor 6 Monaten

yo!

Profilbild von keaukraine
keaukrainevor 6 Monaten

Impressive demo! How expensive is this Chisel tool from World Labs?

Profilbild von Ian Curtis
Ian Curtisvor 6 Monaten

Check out this, you have access via free account

Profilbild von S_S 🌊🌊
S_S 🌊🌊vor 6 Monaten

Love these‼️

Profilbild von felix negentropy. weallareeuropean
felix negentropy. weallareeuropeanvor 6 Monaten

cool but really useless.

Profilbild von The Qubits Guy
The Qubits Guyvor 6 Monaten

Dreaming of a Qubits World

Profilbild von Taro Bushidō
Taro Bushidōvor 6 Monaten

That's Bushido-level precision. Keyboard switching with continuous face-tracking usually kills frame rates. You kept it locked.

Ähnliche Videos

🏎️ | 260624 | Since yesterday, a mysterious figure has been spotted at Zhuhai. My initial assumption was that he had been behind the wheel, as he was wearing racing boots in the photos shared by YIBO OFFICIAL. However, no videos or photos showed him getting in or out of the car just yet; all footage just showed him interacting with Yibo, Rio, and the rest of the UNO Racing team. Now, after research, I can confirm that the Mercedes-AMG factory driver accompanying UNO Racing during these private test sessions is Ralf Aron. He is also using his 2023 helmet for the practice sessions. Ralf Aron is an Estonian professional racing driver and Mercedes-AMG Performance Driver with experience across single-seater, endurance, and GT3 competition. After beginning his career in karting at the age of six, he rose through the junior formula ranks, winning the 2015 Italian Formula 4 Championship before competing in the FIA Formula 3 European Championship. Following his single-seater career, Aron expanded his expertise by taking on management and technical roles with Prema Racing and Sauber Motorsport, contributing to championship-winning campaigns in Formula Regional and the European Le Mans Series. In 2023, he returned to full-time competition as a Mercedes-AMG Junior Driver, finishing runner-up in the ADAC GT Masters and competing in the GT World Challenge Europe Endurance Cup. Promoted to Mercedes-AMG Performance Driver in 2024, Aron has since competed in major international endurance events, including the Nürburgring 24 Hours, the 24 Hours of Spa, the Macau GT World Cup, and the Rolex 24 at Daytona. His current racing program includes GT World Challenge Asia, the Nürburgring 24 Hours, GT Open, and the Asian Le Mans Series, representing teams such as GetSpeed, Climax Racing, and Lone Star Racing. #WangYibo #WangYibo王一博 #王一博 #หวังอี้ป๋อ #ワンイーボー #왕이보 #85RACING #YIBO85

YIBO85: The Archives 🐍

12,755 Aufrufe • vor 3 Monaten

Fast Company just published a great piece on World Labs , Fei-Fei Li , Marble, and the idea that spatial intelligence / world models may be one of the next big shifts in AI. I was happy to be quoted in the article, but I also wanted to share more context about my own experience with World Labs and Marble, and why this direction is especially interesting to me. My starting point: volumetric capture — For the past few years I’ve been exploring and using volumetric capture and reconstruction (photogrammetry, NeRFs, 3D Gaussian Splats) mostly capturing locations around Montreal. Alleys, museums, urban interiors. I love every step of it: the capture itself, the pipeline, and what can be done with the output. Turning real spaces into real-time explorable systems. I do this personally, sharing explorations here, and professionally as chief technologist, and co-founder of Dpt. Physical reality + generative manipulation — In my work I’m especially drawn to mixing physical reality with generative and digital manipulation: using physical interfaces (light, clay, ink, ... ) to drive generative AI pipelines, building mixed reality prototypes that reshape your surroundings, or starting from real captured spaces and transforming them using tools like Marble. Like many people, I saw the World Labs announcement on Twitter in September 2024, and Marble when it surfaced in early December. But by then, I already had a sense something was coming. The first conversation — As someone deep into volumetric capture and radiance fields, I obviously knew about Ben Mildenhall and his pioneering work on NeRF. To my surprise, Ben reached out to me in late June 2024. He’d been following some of my experiments and wanted to chat about my process and workflows and how I was using this “stuff” creatively. At that point he didn’t share what he was building, but we had a genuinely great conversation about radiance fields, AI, and my work. He was curious about the creative perspective, not just the technical one. When the World Labs announcement dropped a few months later, it all made sense. I understood what Ben had been working on, and why the creative angle mattered to them. Then in August 2025, he invited me to try the Marble beta, and I’ve been experimenting with it since. Experimenting with Marble — The first thing I used Marble for was materializing scene and world concepts during ideation at the studio, and seeing if and how it could fit into our production pipeline. In parallel, I dove into a series of experiments focused on world manipulation: starting from real captured spaces and transforming them using Marble. I’d already been exploring that idea using img2img diffusion with ControlNet on NeRF renders, real-time video streams, and even mixed reality using headset camera feeds. But Marble brings something different. It generates persistent, spatially cohesive 3D worlds that can be rendered in real time across a wide range of devices. That’s a real shift. Experiment 01: Parallel Realities — The first experiment, Parallel Realities, starts from a volumetric capture of a real location, reconstructed as 3D Gaussian Splats. Using Marble, I generate an alternate version of that same space, something informed by the original architecture: abandoned, nature-reclaimed, alternate era. Then, using Spark (World Labs’ 3D Gaussian Splatting renderer for THREE.js) I make both realities coexist in the same spatial coordinate system. From there, I use a portal UX mechanic to let the user step between the real reconstruction and the Marble-generated version. Experiment 02: Hidden Depth The second experiment, Hidden Depth, does not transform a space as much as expand it. A captured location has a visual boundary (a mural, a doorway, a dark corridor) and Marble generates what exists beyond it. For example: a Montreal alley has a painted mural; step through it and you’re inside a world informed by what is actually depicted there. World Labs showcased part of this work here: And in their Spark 2.0 post: The project page is here: Why this matters to me — Being able to start from a real 3D Gaussian Splat scene and manipulate it with Marble opens up a lot of ideas. The 3DGS pipeline is becoming an increasingly compelling foundation for exploration, experimentation, and storytelling. What matters most to me right now is more control. The more I can steer the generated scene or world, the more useful the tool becomes. I want more features like the already existing multiple input images and Chisel, the blockout-based approach. I would like better local control, the ability to expand a generated world more and more while preserving coherence, and the ability to directly import 3D Gaussian Splat scenes to be used as a starting point. I want more ways to shape the result, not just a “prompt and hope” approach. — It is exciting to see this field moving from research and demos toward actual creative workflows.

Hugues Bruyère

69,960 Aufrufe • vor 3 Monaten