63 comments

[ 3.0 ms ] story [ 63.5 ms ] thread
Someone: Please combine microscopy with gaussian splatting.
From the link: "Shot from 90 perspectives, 88 focus stacked images each. Nikon Z8, full frame, f/7.1, exposure 1/160, ISO 100, Laowa 180mm macro lens, with LED light and bluescreen." Insane!
What happened to the bottom of that poor strawberry?
What? KIRI Engine makes splats. I always wondered what 3DGS might mean.

Yes. I knoweth what "splats" are: They are splats of fuzzy blobs on the display surface.

Lovely! How was the mechanical setup to ensure that all those shots are consistent, and how long did it take?
Can you show the setup?

(Can we do a Gaussian Splat of the setup of the photograph for the Gaussian Splat of the Strawberry?)

(comment deleted)
Gaussian splats look really good from a distance, but as soon as you zoom in, they really fall off a cliff :/
this is awesome, I wonder what's under there, looks black, maybe thats where they mounted and rotated the strawberry...
Dany, this is so cool.

I'm wondering if the splat community has decided this paper is valuable -- https://github.com/fraunhoferhhi/Self-Organizing-Gaussians -- looking at all the detail in the strawberry splat made me wonder how small one can get the download, and what the current state of the art is for compression.

My intuition is that in theory focus stacking should not be necessary as preprocessing step for 3dgs (or photogrammetry). Does anyone know if there is any recent developments in this regard?

Focus stacking generally is not perfect process and can lead to artifacts/errors and I'd imagine those can then compound when stacked images are used for 3dgs. Also the image focus actually provides some depth data in itself that could be useful?

(comment deleted)
Beautiful.

What I love about gaussian splats is the way they degrade - instead of a hard cutoff or LoD changing spheres into cubes etc., they get increasingly "dreamy" - the basic idea is still there, just less detailed.

Take for example this scene:

https://superspl.at/scene/e721ea7c

If you navigate closer to the trees, things around you become blurry - as if the very fabric of reality unraveled.

Imagine if we start designing GPUs around this technology as opposed to vectors. Imagine what voxel engines would look like. Would love a simulated experience or a small scale that theorizes about this.
I built PlayCanvas in 2011 to power video games. Here we are in 2026 and it's powering strawberries.
I'm really interested to see what folks can do with animated Gaussian splats: https://youtu.be/X8yRlA7jqEQ?si=dXeHa03jO7MTBNLA

The filesize of a 3d animated splat is seemingly very small, and the method enables ~arbitrary FPS. But it seems the setup required to record it is still huge and expensive, which limits its usefulness.

Even with that there are some interesting use cases, eg. I'd love to be able to watch concerts this way, and freely move around the stage and crowd from any angle.

You can do it with a phone camera, ffmpeg, colmap, and opensplat on an m4 macbook air easy enough. I got a nice render of my logitech mouse from it.
This doesn't work at all for me (Linux desktop, tried with Firefox and Chrome). I only see "fullscreen-extended blurry thumbnails" of the splats.
There is a faint sensation of translucency, I wonder if that's an artefact of the process, or if it's the actual optics of the surface layer if the strawberry...
(comment deleted)