Hacker News: danybittel

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Wed, 20 May 2026 04:58:26 +0000

Those are artefacts. Splats are not perfect around reflections.

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Wed, 20 May 2026 04:54:52 +0000

Love these!

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 19:05:04 +0000

I also have them on x: https://x.com/DanyBittel/status/2055624819941483005 I thought direct image links are more welcomed here.

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 17:51:09 +0000

Oh, that would be amazing! The photos are also available and some people definitely take it for a test ride. However.. This dataset with the stacking is far from generic.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 17:48:21 +0000

The light doesn't need to be completely flat like what you'd do when scanning it more traditionally, for meshing. The problem is when the highlight is sharp and reflects it's surrounding. You could remove it, with cross polarization.. But then it wouldn't look realistic anymore.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 15:06:33 +0000

There is actually still a Lytro type camera for industrial application available: https://raytrix.de/ Too low res, too expensive for my use case unfortunately.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 14:59:34 +0000

That's what I thought too.. supersplat has no way to set it to CC0 otherwise.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 13:50:14 +0000

Thanks! I use the computer only to setup the shot, adjust lighting make test stacks of different angles. If everything is good, I disconnect and capture to the memory stick. During the shooting I only adjust the beginning or end of the rail a bit, so everything is in focus at some point. Triggering (manually) the rotary disk still happens from the computer.

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 13:15:44 +0000

I glue mounted the strawberry on three nails and used pins to secure it. I have to think about your idea.. I don't think friction would be enough to hold it in place.. it would probably be hard to knot the top onto something too, as that's where the light is: https://i.imgur.com/vIjw6pc.jpeg

But I'm always experimenting with the mounting, thanks for the inputs.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 13:11:37 +0000

Yes it's shoot in front of a bluescreen.

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 13:07:50 +0000

I usually use PostShot.. but the quality was not very good. I want to try LichtFeld but my Graphics Card has too little memory.. so I reached out on twitter, some people ran tests and Mykhailo got some better quality out of it so I took his training. You can d/l the COLMAP dataset for free and try yourself.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 13:04:22 +0000

I like that they are sort of between a photo and a 3D model. Nothing quite like it.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 12:54:07 +0000

This is an interesting question. There has been some attempt to model the camera better than just a pinhole camera, that could work. https://dof-gaussian.github.io/ https://github.com/leoShen917/DoF-Gaussian

My take.. at a macro scale, the dof is usually so small, that it's hard to get a reliably track. So you'd need some sort of way to tell that these stacked photos belong into a series, and then you sort of are doing focus stacking :-) I do think the alignment algorithm could be improved. Maybe the approaches I linked could be used to make a much more robust focus stacking algorithm, that also corrects for 3D geometry. That would be really cool!

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 12:47:25 +0000

It's an artefact unfortunately. Gaussian splats have no concept of refraction and have a hard time dealing with reflection. Highlights, usually so so. Something I always wrangle.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 11:37:56 +0000

Thanks! We have two compressed formats, the sog by PlayCanvas and spz with sparkjs. Both now support LODs and compress really well.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 11:35:21 +0000

I posted some pictures.. takes only 20 min!

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 11:34:35 +0000

It is in fact still on it's mount and slowly rotting / molding.. for a second capture :-)

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 11:33:17 +0000

Yes mounting.. and I can't quite reach all the way from below.

New comment by danybittel in "Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 11:30:39 +0000

I have done 2x macro (an ant).. and want to try 5x.. but as you get closer, the depth of field becomes really shallow. You can do focus stacking but you risk that the individual areas in focus are less ideal aligned and the tracking can't make any sense out of the geometry anymore.

New comment by danybittel in "Show HN: Gaussian Splat of a Strawberry"

danybittel — Tue, 19 May 2026 11:23:07 +0000

I just posted some images.. I have actually done my studio, (quality is.. let's say painterly ;-): https://superspl.at/scene/0a3916cd