Axel Barroso-Laguna

Hello, Thank you for the interest in our work! > Could you provide visuliaztion code generating Fig6 in the paper Yes, we plan to add visualization code to the repo....

Yes, you are right, the difference between runs for a single image pair could be more than 1 degree. We saw that when running the network over a large test...

Hello! 1. Sorry for the confusion, I meant (2): > the solver results are constant because R and t among all test image pairs were averaged, and hence, the averaged...

We applied the 50% strategy to the PnP and also the probabilistic solver. See the AUC results below: - PnP (with 50% keypoints and Mutual Nearest-Neighbour): 0.70 (VCRE) - 0.36...

Hello! We are trying to make the visualisation code easy to use - it might take a bit longer since we are also preparing all the CVPR materials first. Sorry...

Hello, We just pushed the visualization code (finally!). If still interested, give it a try. You can use it by setting the flag `generate_3D_vis` to _True_ in the `demo_inference.py` script....

Hello! The overlaps.npz was computed originally in the [Map-free dataset](https://storage.googleapis.com/niantic-lon-static/research/map-free-reloc/MapFreeReloc-ECCV22-paper.pdf). To obtain the overlap, they had to build the 3D models (using COLAMP). Given two images (im0 and im1) and...

Hello! Overlaps.npz are obtained with COLMAP (see my previous comment). Regarding your dataset, do you have a list of images you want to use for training? And if so, do...

Hello! Yes, it is possible. I will add it to the TODO list. It might take a while though since we are not actively working on this at the moment....

Hello, sorry for the late response. Is this problem solved? I couldn't replicate it. It seems that the problem is on the validation data, and not on the training. Have...