search

HpWang-whu / YOHO

[ACM MM 2022] You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
https://hpwang-whu.github.io/YOHO
133 stars 19 forks source link

How should I train my dataset? #9

Open wyaimyj opened 1 year ago

wyaimyj commented 1 year ago

Hello, I would like to use your model to train on my own dataset. My dataset consists of point clouds from different viewpoints of a statue. However, I do not have the corresponding rotation and translation matrices between the point clouds pairwise. How can I address this issue? Thank you!

HpWang-whu commented 1 year ago

Hi @wyaimyj, Thanks for your interest! To train YOHO on other datasets, you can refer to here. For multiview reigstration needs, please refer to https://github.com/WHU-USI3DV/SGHR/issues/4#issuecomment-1659680694. Yours,

a1ibekov commented 11 months ago

Hi @wyaimyj, Thanks for your interest! To train YOHO on other datasets, you can refer to here. For multiview reigstration needs, please refer to WHU-USI3DV/SGHR#4 (comment). Yours,

I have a question on how "cloud_bin_0Keypoints.txt" is created? Thank you!

HpWang-whu commented 11 months ago

Hi @a1ibekov, Thanks for your interest! 'cloud_bin_0Keypoints.txt' contains the point-indexes of 5000 randomly sampled points in 'cloud_bin_0.ply' Yours,