search

AllenXiangX / SnowflakeNet

(TPAMI 2023) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
MIT License
149 stars 16 forks source link

how did you get the test data for the point upsampling task? #18

Open beibeirory opened 1 year ago

beibeirory commented 1 year ago

Thanks for your perfect work. But how did you get the test data for the point upsampling task? PU-GAN provides the training and testing mesh files. Which part did you use in your test data as the ground truth and input point clouds?

test_gt_path: /data1/xp/data/PUGAN/8192_gt_lxc test_input_path: /data1/xp/data/PUGAN/2048_input_lxc

ark1234 commented 1 year ago

I have the same question too, I hope I can get answer too, thanks a lot!

AllenXiangX commented 1 year ago

Hi, sorry for the late response! We get the ground truth point clouds (8192 points) with Poisson disk sampling from the testing meshes provided by PU-GAN.

ark1234 commented 1 year ago

Thanks a lot; I will have a look at PU-GAN