Justin Kerr

Couple things you can try: 1) COLMAP the poses to get a sort of upper bound on quality 2) export the poses from a trained nerfacto model into splatfacto We're...

I haven't tested the pytorch implementation within splatfacto for camera optimization yet, but I'd be interested in what happens if you try! The gradients should be correct for camera optimization,...

Are you using `ns-export pointcloud` for this? it should be saved as a `.ply` file. You can also choose whether to output points in the same coordinate frame as the...

Thanks for the effort on this! @jh-surh regarding " I think the next thing to add to gsplat to address this issue would be multi-image splatting, although I question it's...

1) seems like a question for @cvachha . for 2), it's odd that camera_angle_x is radians and x_fov is degrees. Do you know if there's a difference between these parameters...

Have you tried on a more recent version of nerfstudio? 0.3.4 is pretty old so it's hard to debug

Does depth look reasonable in the output render of the viewer? also if you render a pointcloud of the scene does that look reasonable? pointcloud rendering uses depth under the...

This PR fixes a bug with a race condition in custom viewer element callbacks (eg a ViewerButton which renders the current view), previously this might clash with the standard rendering...

That's odd I don't notice any difference. In fact it shouldn't affect things since the only code that was added to the lock was viser element callbacks, which splatfacto doesn't...

That's strange, maybe the result of a bad merge? It should be defined here: https://github.com/nerfstudio-project/nerfstudio/blob/12195f034f51e229bb9bef3b99925d48979b4a6f/nerfstudio/models/nerfacto.py#L131