GeoTransformer

GeoTransformer copied to clipboard

Thank you for sharing the code. test.pkl、train.pkl、val.pkl exist under the file: /geotransformer/data/Kitti/metadata . How can I make these files for my own datasets？

xiakunwonder

First I want to say this is really inspiring work. I noticed in the introduction section, you mentioned 'it is challenging to detect repeatable keypoints' and 'relaxing repeatability requirement'. I...

hadleyhzy34

How to draw the point cloud like this ?

8

Hi , thanks for your great work. And I would like to know how can I get this kind of visualization result in your paper.  When I...

vision507

How to group data sets after downloading

8

Hello, author: I ran the python files in the Kitti dataset and ModelNet dataset folders according to your requirements, but they did not work and were not classified into the...

yangsihai97

Dear authors, Thanks for open-sourcing your amazing work. I'm experimenting with RANSAC and I noticed some unexpected results compared to the paper. What I've done is first change the number...

jinhong-ni

Distributed error

2

Hi, when i use the distributed mode with running CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node 3 trainval.py, the error below occurred. Do you know the reason? [2022-09-23 09:28:23] [INFO] Reducer buckets...

chalth

Is the batch size works?

1

Hi, thanks for sharing your great job. I tested the experiment with 3DMatch dataset from PREDATOR, however, I am trying to test it but I have faced a problem related...

trocolit2

Does gt_transform used during inference?

2

sss725725

Should the value of num_iterations be set to 1000 or 50K? ``` def registration_with_ransac_from_correspondences( src_points, ref_points, correspondences=None, distance_threshold=0.05, ransac_n=3, num_iterations=10000, ): r""" Compute the transformation matrix from src_points to ref_points...

Sucasx

为什么在训练的第二个epoch时显示cuda out of memory

11

lemonade-lm