Those are artefacts. Splats are not perfect around reflections.

Love these!

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

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.

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.

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

Yes it's shoot in front of a bluescreen.

Any suggestions to capture and reproduce very small details in the object? Something works well for you?

Nice.

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.

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

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!