Andréas Meuleman

Hello, The test set seems to be too large for long sequences. I will add an option to change the frequency of test frames and to skip frames in two...

Reducing the number of iterations and skipping frames will make the optimization faster. I will create a parameter to speed up all scheduling and learning rates. For skipping frames, this...

Yes, the format should match NeRF synthetic dataset https://drive.google.com/file/d/13VLTNH2oWu-hNSx0USM9klvrI0cd4T0v/view?usp=drivesdk

Hi, I added the `test_frame_every` argument to reduce the frequency of test frames and decrease CPU memory usage. I also added `prog_speedup_factor` and `refinement_speedup_factor` to reduce the number of iterations...

I added parameters to speed-up optimization. They are described [here](https://github.com/facebookresearch/localrf/issues/6#issuecomment-1611129641).

It looks like you are using a different environment. Could you please list installed python packages and their versions?

Scheduling is defined per frame with parameters such as `--n_iters_per_frame` and `--add_frames_every `.

After we stop adding frames, we optimize poses and the current radiance field for `n_iters_per_frame * ` iterations.

We us the cameras specifications for fov. What camera was your scene captured with? Number of iterations can be changed with `add_frames_every` and `n_iters_per_frame` impacts the number of iterations between...

Hi 1. Poses are up-to-scale (which is typical for monocular RGB pose estimation) 2. It should be in NeRF format. To align poses that have different orientations and scales, you...