[johnb231]

It's not pointless. This is research.

Here's something interesting from the conclusion of the paper:

"An interesting and promising direction for future work that leverages the inherent differentiability, would be to apply RenderFormer to inverse rendering applications."

That means generate a 3D scene from 2D images.

[timhigins]

This has been researched quite a lot with the adjacent task of structure from motion (2d videos) - see NeRFs, Gaussian Splatting - and now there are a few models that do 3d from single 2d images fairly well.

[mhl47]

And interestingly it's still not even close to what a good human artist could do in this task having the same data.