Live data from Hacker News

Show HN: Gaussian Splat of a Strawberry

superspl.at

41–50 of 211 posts

Re: Show HN: Gaussian Splat of a Strawberry

#43
post #37

I read [1], but I still don't quite know what I'm looking at. My guess is a 3D model reconstructed from lots of detailed pictures? [1] https://en.wikipedia.org/wiki/Gaussian_splatting

Lots of translucent blobs composited to produce the appearance of a strawberry.

There is no mesh or model. The visual surface of the strawberry could be made up of blobs spaced far apart physically and not where the surface appears to be.

This is why they are called radiance fields, they model the light not the geometry.

Practically the blobs positions/rotations can be constrained to better physically match the geometry of a strawberry.

Re: Show HN: Gaussian Splat of a Strawberry

#44
post #43
post #37

I read [1], but I still don't quite know what I'm looking at. My guess is a 3D model reconstructed from lots of detailed pictures? [1] https://en.wikipedia.org/wiki/Gaussian_splatting

Lots of translucent blobs composited to produce the appearance of a strawberry. There is no mesh or model. The visual surface of the strawberry could be made up of blobs spaced far apart physically and not where the surface appears to be. This is why they are called radiance fields, they model the light not the geometry. Practically the blobs positions/rotations can be constrained to better physically match the geome…

I'm not sure i agree. The blobs are exactly where the surface appear to be because they are constrained by multiple viewing angles.

Otherwise the splat would fall apart as soon as the viewing angle is changed slightly (Which it absolutely does in many examples on supersplat, you cannot really create an out of distribution view with 3GS, it's not magic)

Re: Show HN: Gaussian Splat of a Strawberry

#46
post #31

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…

If you don't focus stack and try to train on partially unfocused images, the optimizer will try to match the rendered view to be also partially unfocused.

You would have to mask out the blurry areas for each image. I guess one could just implement a feature where the optimizer only optimizes gaussians within the sharp distances relative to the camera.

Re: Show HN: Gaussian Splat of a Strawberry

#48
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.

Re: Show HN: Gaussian Splat of a Strawberry

#49
post #39

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.

I don't know anything about them but it's a cool effect. At least on this strawberry, you're not zooming in but rather traveling closer. I don't see the increasing (made up) detail you'd expect from a zoom, we sort of pop through the skin into an invented interior.
Post reply on HN