Closed jubelsM closed 3 months ago
Hi, thank you for raising this issue.
We used the rotation loss from the MapFree paper (Arnold et al., "Map-free visual relocalization: Metric pose relative to a single image") which minimizes the angular error between the two rotation matrices. The formula should indeed look like this (with a slight abuse of notation):
The version in the code is correct, you should be able to reproduce the fine tuning results with the scripts provided in the repository.
Hi, in the paper (eq 6). it is stated the rotation loss is L1 for both the rotation and translation, in the loss.py the PoseLossMapFree/PoseLossMapFree_C2F uses angular loss. Which loss should I use when trying to reproduce the results of fine-tuning on a single scene?