dmarcos

Contacts and especially lasik are growing in popularity. Strong signal people don’t enjoy wearing glasses if they can avoid it

And contact lenses and lasik are popular because many don’t want to wear glasses. I see head mounted displays useful in constrained scenarios (e.g construction site and tasks where you already wear safety glasses and need free hands). I have a harder time seeing a world where people ditch phones and start voluntarily wearing glasses which is often uncomfortable and inconvenient. Just finished 5 miles run on treadmill, went to sauna and did bouldering. There’s no room for glasses but can occasionally check my phone.

obj is traditional geometry (vertices, triangles). gaussian splats is a different way to represent 3D information (simplifying. it's a point cloud where each point it's an ellipsoid with view dependent color)

A-Frame integration coming soon!

With any demo / example in particular?

You definitely could prototype something like that. Would be really cool to see.

Strange. I also have an iPhone I haven’t seen any issues. Are you using a different browser than Safari or any particular configuration?

Number of splats in the scene and distribution have an impact on performance. Probably in your case you turned the camera in a direction with less splats. There's definitely work to do to deliver consistent performance. We'll probably look into an LOD system next.

Yes. We have demos working already. Those 3D gaussian videos (or 4D that some people call) are really big so we're figuring out what's the best way to distribute and make it a great experience.

Thanks! It works for both! An under-explored area is converting into splats assets created in “traditional” ways (e.g blender). Better visual results in some scenarios (high freq detail). See the furry logo in the homepage carousel.

Thanks! Notice 12MB steak sandwich is the biggest of them all. Rest are < 10MB and several of those very compelling in the 1-3MB range (e.g: Iberico Sandwich 1MB, Clams and Caviar 1.8MB).

Fancier compression methods are coming (e.g SOGS). This is 30MB!

https://vincentwoo.com/3d/sutro_tower/

A-Frame is an entity component system on top of THREE.js that uses the DOM as a declarative layer for the scene graph. It can be manipulated using the standard APIs and tools that Web developers are used to. Initial target was onboarding Web devs into 3D but found success beyond. The super low barrier of entry (hello world below) without sacrificing functionality made it very popular for people learning programming / 3D (part of the curriculum in many schools / universities) and in advanced scenarios (moonrider.xyz ~100k MAUs (300k MAUs at peak) most popular WebXR content to date is made with A-Frame)

One of the Spark goals is exploring applications of 3D Gaussian Splatting. I don't have all the answers yet but already compelling use cases quickly developing. e.g photogrammetry / scanning where splats represent high frequency detail in an appealing and relatively compact way as you can see in one of the demos (https://sparkjs.dev/examples/interactivity/index.html). There are great examples of video capture already (https://www.4dv.ai/). Looking forward to seeing new applications as we figure out better compression, streaming, relighting, generative models, LOD...

A-Frame hello world

<html> <head> <script src="https://aframe.io/releases/1.7.1/aframe.min.js"></script> </head> <body> <a-scene> <a-box position="-1 0.5 -3" rotation="0 45 0" color="#4CC3D9"></a-box> </a-scene> </body> </html>

We have a template for R3F you might find useful:

https://github.com/sparkjsdev/spark-react-r3f

We renamed due to a name collision with another renderer / tool.

Yes. I collaborated with one of the devs at World Labs on this. The goal is to explore new rendering techniques and popularize adoption of 3D gaussian splatting. There's no product associated with it.

Yeah. And some of the individual scans like Clams and Caviar or Pad Thai are < 2MB.

Nothing top of mind like that. Check out people's scans at https://superspl.at/ Anything there should also render in Spark.

It does work in VR! We'll have a demo available soon.

Yes there are several phone apps to generate splats. Also Luma 3D capture.

Just WebGL2

The food scans are just photos from a Pixel phone processed with postshot (https://www.jawset.com/) to generate the splats

There's a community of people passionate about scanning all short stuff with handheld devices, drones... Tipatat let us generously use his food scans for the demo. I also enjoy kotohibi flower scans: https://superspl.at/user?id=kotohibi

Edit: typos

We're definitely looking at it. No specific plans yet

Thanks. We have to definitely add an FAQ

AI will probably enable new workflows and forms of expressions. “Old” ways will still likely be around in some form. Photography didn’t kill portrait painting or movies theater.

It makes me sign up to do anything. That's a deal breaker.

Not that I'm aware of. I like glitch because the dev experience is the same as working on a local machine: a list of files, text editor, viewer. Anything you learn on glitch transfers directly to local development.

Codepen, jsfiddle abstract away too much with the UI and different panels. You're coding their way.

Thanks so much for sharing. Means a lot

Glitch has been a key piece of the A-Frame community (open source project I maintain) for almost a decade. I'm super thankful to the team! So many people started programming and had first steps in game and 3d graphics development with Glitch.

It's sad to see it go. I was always somehow worried. They had an awesome and super generous free tier. You don’t even need to create an account! Unfortunately, it looks they couldn't make the numbers work.

AI is just another form of automation that replaces more of the manual labor. Humans still driving it. How do you feel about photography that replaced portrait paintings? Or photoshop filters? Or computer animation vs hand drawn? I don't see any difference with AI. You can indeed let the AI output stuff automatically but it's as interesting as stock photography. Do you disagree with Carmack's assessment?

"AI tools will allow the best to reach even greater heights, while enabling smaller teams to accomplish more, and bring in some completely new creator demographics"