XuyangBai

Hi @chrischoy, thanks for your sharing. I have a related question for Table 3. Why is the computation time for `FCGF` is much longer than `RANSAC` (6.38s vs. 1.37s)? I...

Hi @chrischoy I mean the `RANSAC` and `FCGF` in Table 3, aren't they both experiments on KITTI?

Hi @tmbdev Thanks for your reply. I have tried `num_workers=0` but it does not work. I will try the other solutions and give you feedback. I does not care whether...

I mean after setting `num_workers=0`, the network still stops and never continues. I solve the problem by using a smaller shard to make sure `world_size

Yes I know that the varifocal loss is proposed to predict a class-aware iou value but I think it is also able to use for the seperated iou prediction branch...

Hi @lijx10 Thanks for your sharing. Are you also going to share the evaluation code?

Hi, I didn't see the example. Could you specify which point clouds pair you are using so that I can see it on my environment

Hi, You can download the raw dataset and run https://github.com/XuyangBai/PPF-FoldNet/blob/master/script/fuse_fragments_3DMatch.py to compute the point clouds and the corresponding poses, from which you can compute the GT transformations.

Hi @edshkim98 Thanks for your interest in my implementation. But I implemented this version very long time ago and have no time exploring the performance now. Would you mind trying...

Hi @Chris45215 thanks for your interest, Free feel to open a PR for the marker-based alignment methods.