I know, I don't get the fuzz either, I've coded real-time gaussian splat renderers >7 years ago with LOD and they were able to show any kind of point cloud.
They worked with a basic 970 GTX on a big 3d screen and also on oculus dk2.
Photogrammetry struggles with certain types of materials (e.g. reflective surfaces). It's also very difficult to capture fine details (thin structures, hair). 3DGS is very good at that. And people are working on improving current shortcomings, including methods to extract meshes that we could use in traditional graphics pipelines.
3DGS is absolutely not good with non Lambertian materials..
After testing it, if fails in very basic cases. And it is normal that it fails, non Lambertian materials are not reconstructed correctly with SfM methods.
You use SfM to find the first point cloud. However SfM is based on the hypothesis that the same point 'moves' linearly in between any two views. This hypothesis is important because it allows you to match a point in two pictures, and given the distance between the two images, you can triangulate the point in space. Therefore find it's depth.
However, non-Lambertian points move non linearly in viewing space (eg a specular point depends on the viewer pose).
So, automatically, their positions in space will be false, and you'll have floating points.
Gaussian 'splats' may have the potential to render non-Lambertian stuff using for example the spherical harmonics (even if I don't think the viewer use them if I'm not mistaken). But, capturing non-Lambertian points is very difficult and an open research problem.
* Do not allow questions on GitHub issues, it's a poor place for conversations. I find Discourse or some other forum (or mailing list) a better place to do that, which allows community participation (and you can automate moderation using something like https://github.com/pierotofy/issuewhiz)
* People owe you nothing, just as you owe them nothing; you don't have to fix an issue or merge a pull request because somebody opened one.
* Try review and merge contributions, but on your own timeframe. If people have urgency, kindly invite them to get a paid support agreement.
* Don't engage in quarrels; you always have the option to ignore or ban the offenders.
While it's certainly challenging, it's not terrible, but it requires some thought and a sustainable business model, something many FOSS developers don't want to do. https://piero.dev/category/foss-funding/
- It's not clear what the character limit would be if one was to sign-up.
- What does "context-driven translations for higher accuracy" mean?
- 35 characters are quite short for testing the translation of a complete sentence. Is there a reason for using such a short character length?
The character limit for an api call is 3000. I put it in the docs but could probably make it more obvious.
The context driven for higher accuracy is referencing what's going on under the hood, but on second thought it doesn't make much sense to put that there if I'm not going in depth about the under the hood stuff. I'll take that out.
35 character is quite short, you're right. I'll double it. The reason it was so short was arbitrary. I made it 100 now.
Check https://github.com/pierotofy/OpenSplat for something you can run on your 10 year old laptop, even without a GPU! (I'm the author)