Richard Higgins

 If you use the checkpoint reimager mentions you can get results like this! Thanks reimager.

Looks like your python cant find the `Pillow` package which is imported as PIL. The fix here is probably `pip install Pillow` but depends on your OS if that works....

Ahh okay cool! I think that something went wrong between steps [3] and [4] then. You probably want to rerun `python setup.py` from inside the dream-factory directory. When you run...

It has to be a NVIDIA GPU, at least for the version of PyTorch that gets installed through `setup.py`. You might be able to run everything on the CPU, though...

Also it's interesting that going from 2 images with the `PairViewer` and 3 images with the `ModularPointCloudOptimizer` the scale of the reconstruction often changes quite dramatically! Easy to fix if...

This is really helpful! I've gotten further than before. ``` > /home/relh/Code/???????????/dust3r/dust3r/cloud_opt/init_im_poses.py(61)init_from_known_poses() 60 assert known_poses_msk[n] ---> 61 _, i_j, scale = best_depthmaps[n] 62 depth = self.pred_i[i_j][:, :, 2] ipdb> print(n)...

I switched to mast3r which uses a cache and it seems to have sped up things when using more than 2 images

I don't really like this because we have to call next() on the iterator once and basically throw away the first value before being able to index, but it's a...

I added a new flag `map_access` everywhere. Also the TFRecordMapDataset now has a `try:` block for the first next(iter), though I think we don't need it because I changed the...

This was broken but now it actually can send to the inner iterator