Unfortunately not yet. Also code alone without the training data and weights might still requires considerable effort. I also wonder how diverse their training data is, i.e. how well the solution will generalize.

I don’t do video game programming but what I have heard about engines is that lighting is controlled by the game engine and it’s one step in the pipeline to render the game. Ray tracing is one technique where the light source and the location of the 3d model has simulated light rays in relation of the light source and model.

They are probably rendering with a simple lighting model since this is a system where lighting in a game is handled by another algorithm

Gaussian splats can pretty much be rendered in any off the shelf 3D engine with reasonable performance, and the focus of the paper is generating the splats so there's no real reason for them to mention runtime details

I noticed that too. It also doesn't seem to always know how to map (or remove) certain things, like the hair bun on the input image, to the generated avatars once you get outside of the facial region.

Wear a hood and sunglasses at all times in pubic spaces so that it would be hard to make a good shot of you from three sides. A complex, dynamic hairdo would also be helpful. That is, if you're at risk of being impersonated, e.g. if you possess or control something valuable. Better yet, devise non-obvious verbal protocols that should be followed by you and your counter-party a decision about something important is to be discussed over a video call. Even if that counter-party is your parent or co-founder. Maybe especially then.

Another box of nails into admissibility of video recordings in court, sadly.