วีดีโอ

WOW great job this is verry impressiv. I don't Belive what my Eyes see....

I was here before it went mainstream. It's awesome!

This looks amazing!

👏🏻👏🏻👏🏻

Very simplistic explanation.

VR and Google Maps in a few years will be awesome

Cyberpunk 2077 brain dance irl

Great job, i cannot wait to try it, When will the code be released?

1. Wouldn't it be more accurate to compare 3dgs to nerf when both are either initialized at random or both with sfm points? 2. Since this method is based on rendering and not ray tracing, how can it do such a good job at modeling the sun reflecting of a shiny object like the countertop only at certain angles?

I would like to know what equipment this was taken with

So neat, I'm not even 100% sure that I know what I'm looking at?

Okay

Damn thats cool

Oh my God. I'm shaking right now

beautiful

Deckard: Enhance...

Mind blowing

Will this be available for public/professional use soon?

That's amazing! Good job : O

🤯

The future of gaming just got set.

can we generate the point cloud instead of capture it from real life? i'm thinking of game development use cases

Streetview is about to become the biggest game map ever

every damn day we get closer to a hype realistic optimized vr game

Amazing

Can anyone say unlimited detail?

Waiting for this rendering tech to be available in Blender, Unreal and Unity 😊

Every day we get closer to the holodeck

in the 90s

What's a gaussian? 😐

I wonder if you could say train an ai on Gaussian splatters of animals that come from the input of dna sequences if you could get it to output mammoths

The future will be representation. I wonder if there is enough viewing angles on smartphones for real time representation.. or maybe a sort of setup with multiple cameras? Or maybe the LiDAR on an iPhone has enough depth for representation ?

What a time to be alive!

Just imagine the future: an instant 3D models mrom a mobile phone camera!

Problem: neither PSNR nor plain SSIM, while very easy to compute, are particular good measures for subjective image similarities - someone better run these tests with more meaningful metrics like MS-SSIM & VMAF (which on top of being more close to human perception of visual differences are also used in many existing image quality, restoration & compression tests).

Awesome! I want to see those scenes in VR! 🥽

*makes fake vengeance p*rn using photos of a bedroom*

finally something that is easy to interpret and to work with. no idea how come they are able tor render novel views that fast. if every scene has >100k splats, I would pre-render them into bilboard sprites, but how come reflections are so good?

The future of photography 😱

I don't understand any of the technical terms but that looks like dark magic to me. This is like, good enough to use in high end films now.

Wtf this is like pure magic. Amazing work, can’t wait to see it in action!!

can we say that is just amazing !!

Waiting for a tutorial for how to setup 😍

wow

C'est magnifique

what gets optimized during backprop?

amazing

What an incredible achievement, how do I get my hands on this? :o

any comparisons with mobilenerf?

How are non-lambertian (i.e. viewpoint dependent) effects, like fresnel, specular, etc. achieved with this approach? It appears as though the technique struggles to represent glass (e.g. the reflections and transparency of the windscreen as shown in the project page). I suppose one approach may be to optimize spherical harmonics coefficients which are later pruned after training, though this may result in really bad ringing. Or you could have a "cone of influence" (cone orientation quaternion, anisotropic cone fov) that defines the opacity of a given gaussian depending on the viewing angle. Unfortunately this would likely massively increase the number of gaussians you'd need for certain surfaces, and you may need to know how many to allocate for these surfaces ahead of time for initialization. Third, you could have a very sparse voxel grid of learned functions that converts the viewing angle from the gaussian center position, and the gaussian center position within the voxel cell, to rgba. This may be the fastest, as you'd only need to evaluate this once per gaussian per frame, not per pixel.