Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Quest's Browser 34.2 was released today with experimental support for unbounded spaces. This allows you to create large scale AR experiences that are no longer limited to the guardian boundary.

@[email protected]

1,382 subscribers

72,704 views • 2 years ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

@[email protected]2 years ago

To enable it, go to chrome://flags, check "WebXR experiments and restart the browser. Then ask for support 'unbounded' when you call requestSession. See

@[email protected]1 year ago

FYI this feature shipped in 36.2 so it should available to everyone. Any WebXR that uses passthrough can now be bigger than the guardian boundary.

@[email protected]1 year ago

36.2 also supports dynamic foveation (previously limited to 3 hardcoded values) and requestViewportScale:

@[email protected]2 years ago

Cc @mrdoob should we make it a default optional parameter in @threejs ?

lorcopola cage2 years ago

Had to focus on the XR stuff as Your home looks insanely huge ^^

AndrewTek 🇺🇸2 years ago

That was great! The best part was the occlusion by the real-world walls. What setup is needed in ThreeJS/AFrame to support that?

@[email protected]2 years ago

It’s built into three. Just request the feature and depth sensing will be active

Mike Chaves2 years ago

LETS GO!

Francois Laberge ✍️2 years ago

Fuck yeah, awesome!

VanilladadMD2 years ago

This is the future

Related Videos

#Quest Browser 40.4 was released with support for real time hit testing on Quest 3 and 3s. You no longer have to scan the room if you want to use the #WebXR hit test API since we will measure the room while doing hit testing.

#Quest Browser 40.4 was released with support for real time hit testing on Quest 3 and 3s. You no longer have to scan the room if you want to use the #WebXR hit test API since we will measure the room while doing hit testing.

@[email protected]

19,799 views • 11 months ago

🎇 Your memories are essentially digital. 🕊 Don't let them fly away with you. ✨ We are pleased to reveal Time Guardian, the solution that allows you to transmit your digital legacy.

🎇 Your memories are essentially digital. 🕊 Don't let them fly away with you. ✨ We are pleased to reveal Time Guardian, the solution that allows you to transmit your digital legacy.

Time Guardian

238,321 views • 3 years ago

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

AK

140,624 views • 3 years ago

What if you could use #AR and #VR technology on the go – even on the road 🚗? We’re working with BMW Group to create AR and VR experiences for passengers to make the time you spend traveling more productive and fun.

What if you could use #AR and #VR technology on the go – even on the road 🚗? We’re working with BMW Group to create AR and VR experiences for passengers to make the time you spend traveling more productive and fun.

Meta Newsroom

254,852 views • 3 years ago

Today, at Permissionless Wealth (自由财富) III we shared the first glimpse of Readyverse Studios multi world experiences, showcasing WIP gameplay from battle royale OPEN, and player traversal to Promptopia, an experimental AI sandbox in The Readyverse, that allows players to create anything imaginable through simple text prompts. 🎮

Today, at Permissionless Wealth (自由财富) III we shared the first glimpse of Readyverse Studios multi world experiences, showcasing WIP gameplay from battle royale OPEN, and player traversal to Promptopia, an experimental AI sandbox in The Readyverse, that allows players to create anything imaginable through simple text prompts. 🎮

The Readyverse

128,840 views • 1 year ago

We are delighted to announce the release today of a new therapy module for Cuespeak, “Scripts”. It allows you to write personalised scripts that turn automatically into exercises to work on saying and writing the text with support. Watch the video! #aphasia #SLPeeps

We are delighted to announce the release today of a new therapy module for Cuespeak, “Scripts”. It allows you to write personalised scripts that turn automatically into exercises to work on saying and writing the text with support. Watch the video! #aphasia #SLPeeps

Cuespeak

13,633 views • 3 years ago

Today marks 5 years since we released 5, Thank you for being on this unique journey with us. The love ❤️ and support from you all is so special and encourages us to keep pushing through life to create the art With love Sault x

Today marks 5 years since we released 5, Thank you for being on this unique journey with us. The love ❤️ and support from you all is so special and encourages us to keep pushing through life to create the art With love Sault x

SAULT

117,645 views • 2 years ago

RobotArena is live today! Led by @sumo43_, RobotArena is an ELO-based 🤖 Robot-Action Model benchmark that allows you to test models directly in your browser. Check it out here: Special thanks to HIVE Digital Technologies for their compute support!

RobotArena is live today! Led by @sumo43_, RobotArena is an ELO-based 🤖 Robot-Action Model benchmark that allows you to test models directly in your browser. Check it out here: Special thanks to HIVE Digital Technologies for their compute support!

skunkworks

34,446 views • 2 years ago

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.

Felix Heide

27,779 views • 1 year ago

Terrifying escalation. The US is moving from airstrikes to a massive ground invasion. They are planning to occupy Kharg Island and send troops deep into Isfahan to dig for uranium. This is no longer a limited war, it is a full scale occupation.

Terrifying escalation. The US is moving from airstrikes to a massive ground invasion. They are planning to occupy Kharg Island and send troops deep into Isfahan to dig for uranium. This is no longer a limited war, it is a full scale occupation.

Furkan Gözükara

32,368 views • 5 months ago

Can I count on you to donate to my Senate campaign? Your support allows me to continue work for veterans, protecting abortion rights, and climate action in the Senate. It also allows me to support other Democratic candidates up and down the ballot this year. Please donate today.

Can I count on you to donate to my Senate campaign? Your support allows me to continue work for veterans, protecting abortion rights, and climate action in the Senate. It also allows me to support other Democratic candidates up and down the ballot this year. Please donate today.

Captain Mark Kelly

1,274,411 views • 2 years ago

We are announcing potpie AI $2.2M pre-seed fundraise to advance Spec-Driven Development for large enterprise codebases. The round is led by Emergent Ventures , with participation from All In Capital , DeVC , and PointOne Capital , along with the support of some amazing angel investors from companies including Atlassian, OpenAI, Meta, Razorpay and Flobiz. As AI accelerates code generation, the constraint inside large enterprises has shifted from coding to maintenance and assurance. The limiting factor is no longer writing code, but understanding complex systems, aligning teams around intent, and safely evolving large, interdependent codebases. In most organizations, specifications exist as static documents, while production systems evolve independently. Context is fragmented across repositories, tickets, logs, reviews, and floating documents making reliable AI adoption difficult. We are building the foundational layer that makes Spec-Driven Development executable at scale. By unifying engineering context and operationalizing the spec as a structured source of truth, we enable AI systems to reason with architectural awareness rather than surface-level code completion. We are already working with large enterprise customers, including Fortune 500 organizations. This milestone allows us to deepen those partnerships and support more teams transitioning from experimental AI usage to structured, production-grade AI-first engineering workflows. If you are leading engineering at scale and evaluating how AI should integrate into mission-critical systems, we would love to chat with you!

We are announcing potpie AI $2.2M pre-seed fundraise to advance Spec-Driven Development for large enterprise codebases. The round is led by Emergent Ventures , with participation from All In Capital , DeVC , and PointOne Capital , along with the support of some amazing angel investors from companies including Atlassian, OpenAI, Meta, Razorpay and Flobiz. As AI accelerates code generation, the constraint inside large enterprises has shifted from coding to maintenance and assurance. The limiting factor is no longer writing code, but understanding complex systems, aligning teams around intent, and safely evolving large, interdependent codebases. In most organizations, specifications exist as static documents, while production systems evolve independently. Context is fragmented across repositories, tickets, logs, reviews, and floating documents making reliable AI adoption difficult. We are building the foundational layer that makes Spec-Driven Development executable at scale. By unifying engineering context and operationalizing the spec as a structured source of truth, we enable AI systems to reason with architectural awareness rather than surface-level code completion. We are already working with large enterprise customers, including Fortune 500 organizations. This milestone allows us to deepen those partnerships and support more teams transitioning from experimental AI usage to structured, production-grade AI-first engineering workflows. If you are leading engineering at scale and evaluating how AI should integrate into mission-critical systems, we would love to chat with you!

Aditi Kothari

41,950 views • 6 months ago

Imagine an apparel brand with 80,000 products trying to generate video ads for each of them! It's humanly impossible for large e-commerce businesses generate video ads at scale today. Excited to announce Bestever AI Commerce today that solves this.

Apoorva Govind

93,442 views • 11 months ago

We are putting on a concert today . If you have contributed to support this event you are the people that are making this possible

We are putting on a concert today . If you have contributed to support this event you are the people that are making this possible

Tommy Robinson 🇬🇧

282,029 views • 2 years ago

Figge shares info on the Otherside Development Kit “The O.D.K is a set of tools that allows you to build in Unreal Engine to create next generation blockchain experiences” “Our vision is for you to be able to drag and drop, upload and go live”

Figge shares info on the Otherside Development Kit “The O.D.K is a set of tools that allows you to build in Unreal Engine to create next generation blockchain experiences” “Our vision is for you to be able to drag and drop, upload and go live”

Jack

17,468 views • 10 months ago

Create movie scenes from image grids with Kling O1. With Freepik Spaces, I created a workflow that requires only a single prompt to do this. Inputting the grid reference into Kling is a great workflow to create cinematic scenes. Comment for the Spaces link 🔽

Create movie scenes from image grids with Kling O1. With Freepik Spaces, I created a workflow that requires only a single prompt to do this. Inputting the grid reference into Kling is a great workflow to create cinematic scenes. Comment for the Spaces link 🔽

Jerrod Lew

16,957 views • 8 months ago