It has 50m splats, captured by XGRIDS K2 camera in roughly 1 hour of walking around.

SOGS compression keeps coming up here as a go-to method for reducing Gaussian Splatting model sizes. I put together a deep dive into how SOGS actually works under the hood, with some practical insights on how it can be used in production.

The article stays fairly high-level, but I'm happy to dive into specifics in the comments. I learned quite a bit from implementing my own version of SOGS compression.

Comments URL: https://news.ycombinator.com/item?id=45426089

Points: 1

# Comments: 1

You can't get a consumer-grade GPU with enough VRAM to run a large model, but you can do so with macbooks.

I wonder if doubling down on that and shipping devices that let you run third party AI models locally and privately will be their path.

If only they made their unified memory faster as that seems to be the biggest bottleneck regarding LLMs and their tk/s performance.

The key goal is that the creators of 3DGS models can use Blurry as a powerful tool to build the 3D experience that is performant, simple, and aesthetically pleasant for end users (viewers).

3DGS models can be shared via a link or embedded on a website, notion, etc..

Link: https://useblurry.com

I noticed that there is a few tools to create and edit 3D Gaussian Splatting[1] models, but not so many tools for robust hosting, sharing, and presentation of these models, so I built Blurry!

Unlike other platforms, I’m specifically focusing on the best 3DGS in-browser viewer experience you can seamlessly embed on websites or Notion docs, with more places coming soon!

Some of the potential use cases are professional training, product and rental space marketing, and construction business. But at this stage with Blurry, I’m specifically targeting people/businesses that already use 3D scanning to a certain degree but are lacking an easy-to-use and performant hosting platform for their 3DGS models.

I’m shipping new features and improvements very quickly. Two big things on the current roadmap are first-person camera controls (especially for indoor splats), and a support for really large models (possibly done by streaming of the model as you move around).

Would love your thoughts and feedback pls!

[1] For those who don’t know, 3D Gaussian Splatting is a fairly new method to reconstruct a 3D model from real pictures and videos (https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/).

Comments URL: https://news.ycombinator.com/item?id=44124880

Points: 25

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=43545349

Points: 338

# Comments: 107

Abstracting all of this complexity away in one general tool/library and pretending that it will always work is snake oil. There are no shortcuts to building truly high quality product at a large scale.

I disagree that this is the accurate way to think about LLMs. LLMs still use a finite number of parameters to encode the training data. The amount of training data is massive in comparison to the number of parameters LLMs use, so they need to be somewhat capable of distilling that information into small pieces of knowledge they can then reuse to piece together the full answer.

But this being said, they are not capable of producing an answer outside of the training set distribution, and inherit all the biases of the training data as that's what they are trying to replicate.

> I guess my point is, when you use LLMs for tasks, you're getting whatever other humans have said. And I've seen some pretty poor code examples out there. Yup, exactly this.

More formats are definitely on the roadmap. At first I'd like to add full support for higher order of spherical harmonics and then I wanted to take a look at other methods, too. Maybe 2DGS and/or SMERF would make sense for comparison purposes.

Explanation of controls makes sense, too. I'll add that.

Regarding WebXR, that's currently not on my roadmap. However, if the demand is there I'd consider adding it

- Adding better controls (and an explanation) makes sense!

- Good job discovering the L control. That's actually something that's not supposed to be public. I use that tool to find the correct orientation of splats before publishing them. But once I find those values saved in the DB, there's no use for that tool anymore. When I make it available to the users I'll defo make the UX clearer.

- Good point about landscape mode. I'll fix that.

One of my future plans is to extend it to other methods than just gaussian splatting so that we can compare methods across a wide range of captures with varying light conditions, different materials, etc..

I think SplatGallery is an exploration of how people use the technology and what can it be useful for today and what is the next step.