I’m fascinated by the aesthetic of this technique. I remember early versions that were completely glitched out and presented 3d clouds of noise and fragments to traverse through. I’m curious if you have any thoughts about creatively ‘abusing’ this tech? Perhaps misaligning things somehow or using some wrong inputs.

Hi David, have you looked into alternatives to 3DGS like https://meshsplatting.github.io/ that promise better results and faster training?

Can such plugin be possible for Davinci Resolve, to have merge of scene captured from two iPhones with spatial data, into 3D scene? With M4 that shouldn’t be problem?

high-quality 3D content

Would have been nice to see some in the video.

Great work! I’d love to see a proper BTS or case study.

Random question, since I see your username is green.

How did you find out this was posted here?

Also, great work!

From the article:

>Evercoast deployed a 56 camera RGB-D array

Do you know which depth cameras they used?

Hah, for the past day, I've been trying to somehow submit the Helicopter music video / album as a whole to HN. Glad someone figured out the angle was Gaussian.

Is he wearing... hair curlers?

And nearly a Carti post at the top of HN

yeah that had me do a double take lol

Why is that “cool” or desirable?

1. Create a point cloud from a scene (either via lidar, or via photogrammetry from multiple images)

2. Replace each point of the point cloud with a fuzzy ellipsoid, that has a bunch of parameters for its position + size + orientation + view-dependent color (via spherical harmonics up to some low order)

3. If you render these ellipsoids using a differentiable renderer, then you can subtract the resulting image from the ground truth (i.e. your original photos), and calculate the partial derivatives of the error with respect to each of the millions of ellipsoid parameters that you fed into the renderer.

4. Now you can run gradient descent using the differentiable renderer, which makes your fuzzy ellipsoids converge to something closely reproducing the ground truth images (from multiple angles).

5. Since the ellipsoids started at the 3D point cloud's positions, the 3D structure of the scene will likely be preserved during gradient descent, thus the resulting scene will support novel camera angles with plausible-looking results.

This is a REALLY good video explaining it. https://www.youtube.com/watch?v=eekCQQYwlgA

Gaussian splatting is a way to record 3-dimensional video. You capture a scene from many angles simultaneously and then combine all of those into a single representation. Ideally, that representation is good enough that you can then, post-production, simulate camera angles you didn't originally record.

For example, the camera orbits around the performers in this music video are difficult to imagine in real space. Even if you could pull it off using robotic motion control arms, it would require that the entire choreography is fixed in place before filming. This video clearly takes advantage of being able to direct whatever camera motion the artist wanted in the 3d virtual space of the final composed scene.

To do this, the representation needs to estimate the radiance field, i.e. the amount and color of light visible at every point in your 3d volume, viewed from every angle. It's not possible to do this at high resolution by breaking that space up into voxels, those scale badly, O(n^3). You could attempt to guess at some mesh geometry and paint textures on to it compatible with the camera views, but that's difficult to automate.

Gaussian splatting estimates these radiance fields by assuming that the radiance is build from millions of fuzzy, colored balls positioned, stretched, and rotated in space. These are the Gaussian splats.

Once you have that representation, constructing a novel camera angle is as simple as positioning and angling your virtual camera and then recording the colors and positions of all the splats that are visible.

It turns out that this approach is pretty amenable to techniques similar to modern deep learning. You basically train the positions/shapes/rotations of the splats via gradient descent. It's mostly been explored in research labs but lately production-oriented tools have been built for popular 3d motion graphics tools like Houdini, making it more available.

It’s a point cloud where each point is a semitransparent blob that can have a view dependent color: color changes depending on direction you look at them. Allowing to capture reflections, iridescence…

You generate the point clouds from multiple images of a scene or an object and some machine learning magic

This 2-minute video is a great intro to the topic https://www.youtube.com/watch?v=HVv_IQKlafQ

I think this tech has become "production-ready" recently due to a combination of research progress (the seminal paper was published in 2023 https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/) and improvements to differentiable programming libraries (e.g. PyTorch) and GPU hardware.

https://aras-p.info/blog/2023/09/05/Gaussian-Splatting-is-pr... and for a visual demo of the result https://antimatter15.com/splat/

For the ELI5, Gaussian splatting represents the scene as millions of tiny, blurry colored blobs in 3D space and renders by quickly "splatting" them onto the screen, making it much faster than computing an image by querying a neural net model like radiance fields.

I'm not up on how things have changed recently

I found this VFX breakdown of the recent Superman movie to have a great explanation of what it is and what it makes possible: https://youtu.be/eyAVWH61R8E?t=232

tl;dr eli5: Instead of capturing spots of color as they would appear to a camera, they capture spots of color and where they exist in the world. By combining multiple cameras doing this, you can make a 3D works from footage that you can then zoom a virtual camera round.

Hi, I'm one of the creators of GSOPs for SideFX Houdini.

The gist is that Gaussian splats can replicate reality quite effectively with many 3D ellipsoids (stored as a type of point cloud). Houdini is software that excels at manipulating vast numbers of points, and renderers (such as Octane) can now leverage this type of data to integrate with traditional computer graphics primitives, lights, and techniques.

My bad! I am the author. Gaussian splatting allows you to take a series of normal 2D images or a video and reconstruct very lifelike 3D from it. It’s a type of radiance field, like NeRFs or voxel based methods like Plenoxels!

Corridor has done some great stuff with Gaussian Splats, I recommend this video for a primer!

https://youtube.com/watch?v=cetf0qTZ04Y

Reminds me of Kurtwood Smith’s piping sales pitch in The Patriot

The aesthetic here is at least partially an intentional choice to lean into the artifacts produced by Gaussian splatting, particularly dynamic (4DGS) splatting. There is temporal inconsistency when capturing performances like this, which are exacerbated by relighting.

That said, the technology is rapidly advancing and this type of volumetric capture is definitely sticking around.

The quality can also be really good, especially for static environments: https://www.linkedin.com/posts/christoph-schindelar-79515351....

Knowing what I know about the artist in this video this was probably more about the novelty of the technology and the creative freedom it offers rather than it is budget.

For me it felt more like higher detail version of Teardown, the voxel-based 3d demolition game. Sure it's splats and not voxels, but the camera and the lighting give this strong voxel game vibe.

We will be able to have imax level 3D technically today if you feed it the correct data

Yes, they talk about this in the article and that’s exactly what they did.

Several of ASAP's video have a lo-fi retro vibe, or specific effects such as simulating stuff like a mpeg a/v corruption, check out A$AP Mob - Yamborghini High (https://www.youtube.com/watch?v=tt7gP_IW-1w)

Loving this; great work! Do you talk about the process anywhere in more depth?

Cool aesthetic!

Similarly, the music video for Taylor Swif[0] (another track by A$AP Rocky) is just as surrealistic and weird in the best way possible, but with an eastern european flavor of it (which is obviously intentional and makes sense, given the filming location and being very on-the-nose with the theme).

0. https://youtu.be/5URefVYaJrA

Watch the video to the very end: the final splat is not a gaussian one.

Good idea - we'll put that link in the toptext as well. Thanks!

I loved the video. Didn't get the motion sickness myself.

My wife said the same thing, but it gets better after the intro.

For sure!

You might consider why this article which has nothing to do with AI as you know it (except for the machine learning aspects of Gaussian splatting), and was produced by a huge team of vfx professionals, has made you think about AI democratising culture (despite the fact that music videos and films have been cheap to make for decades). Don’t just look for opportunities to discuss your favourite talking points.

I really don’t see the connection. A$AP isn’t a noob

I think in 2026 it's hard to make a video look this "bad" without it being a clear aesthetic choice, so not sure you could find this video in another setting.

The technology is impressive, but the end result… Weapons-grade brainrot.

I’m curious what other artists end up making with it.

I prefer when artists make music they intrinsically want to make — not what others want them to make.

It seems the numerous leaks and trials took their toll.

I don’t disagree with you—I felt “Tailor Swif,” “DMB,” and “Both Eyes Closed” were all stronger than the tracks that made it onto this album.

But sometimes you’ve gotta ship the project in the state it’s in and move on with your life.

Maybe now he can move forward and start working on something new. And perhaps that project will be stronger.

Im sure it was more like, “hey babe, can I get a few millions to go in the studio and experiment/make some art?” And then she was like, “yeah go for it! Make some weird shit.”

If I was in his position I’d probably be doing the same. Why bother with another top hit that pleases the masses.

Because it was awesome. But also, leaks probably.

Gaussian splatting is not NeRF (neural radiance field), but it is a type of radiance field, and supports novel view synthesis. The difference is in an explicit point cloud representation (Gaussian splatting), versus a process that needs to be inferred by a neural network.

> and then "NeRF"'d which means to extrapolate any missing data about their transposed 3D model

Not sure if it's you or the original article but that's a slightly misleading summary of NeRFs.

it does, it just doesn't have video

> Pretty sure most of this could be filmed with a camera drone and preprogrammed flight path

This is a “Dropbox is just ftp and rsync” level comment. There’s a shot in there where Rocky is sitting on top of the spinning blades of a helicopter and the camera smoothly transitions from flying around the room to solidly rotating along with the blades, so it’s fixed relative to rocky. Not only would programming a camera drone to follow this path be extremely difficult (and wouldn’t look as good), but just setting up the stunt would be cost prohibitive.

This is just one example of the hundreds you could come up with.

If it was achievable, cheaper, and of equal quality then it would have been done that way. Surely it would’ve been done that way a long time ago too. Drone paths have been around a lot longer than this technology.

There’s no proof of your claim and this video is proof of the opposite.

A drone path would not allow for such seamless transitions, never mind the planning required to nail all that choreography, effects, etc.

This approach is 100% flexible, and I'm sure at least part of the magic came from the process of play and experimentation in post.

Flying a camera drone with such proximity and acceleration would be a safety nightmare.

I think you’re missing the point

Volumetric capture like this allows you to decide on the camera angles in post-production

it gives you flexibility, options

This might be the first time I'm stumbling on Dunning Kruger on HN, no offense.

It's fucking cool. That's why.

This tech is moving along at breakneck pace and now we're all talking about it. A drone video wouldn't have done that.