thuanaislab
thuanaislab
Thank you for your interest in our work. The issue you got shows that you probably forgot to keep the threshold with Superpoint when running Hloc. Note that only when...
I think you forgot to change the threshold of `'keypoint_threshold': 0.005` to `'keypoint_threshold': 0.0`. Additionally, please change the config in Hloc at the parents configuration, the example I have shown...
As long as your image size is not too small, you can manage to get specific number of keypoints as you want.
Hi there, Thanks for your interest - we are intending to release the code in the next few months with a fully updated version and some more interesting results.
Thank you for your interest in this work. We have initially uploaded the source code. However, it's not the final optimal one. If there are any issues plz contact me....
Hi, thank you for your interest in our work. I think you can follow the solution in the issue #9 https://github.com/ais-lab/feat2map/issues/9 This can help you to config the HLOC. If...
try to run only: python runners/7scenes/localization.py --dataset $dataset -s stairs --skip_exists --use_dense_depth It will work :).
For the chess scene, it even takes about 600s to estimate a single camera pose. Any update for enhancement?
I found that if we run multiple pose estimations at the same time (ex: terminal 1 for eval. chess, 2 for stairs). It will lead to extremely slow as above....
Hi, I am using version 1.13