alexzhou907/pvd

pvd's Issues

How to install the module:"_pvcnn_backend"

No module named '_pvcnn_backend'
File "/home//MyProjects/PVD/modules/functional/backend.py", line 22, in
'bindings.cpp',
File "/home//MyProjects/PVD/modules/functional/ball_query.py", line 3, in
from modules.functional.backend import _backend
File "/home//MyProjects/PVD/modules/functional/init.py", line 1, in
from modules.functional.ball_query import ball_query
File "/home//MyProjects/PVD/modules/ball_query.py", line 4, in
import modules.functional as F
File "/home/**/MyProjects/PVD/modules/init.py", line 1, in
from modules.ball_query import BallQuery
File "/home/MyProjects/PVD/model/pvcnn_generation.py", line 6, in
from modules import SharedMLP, PVConv, PointNetSAModule, PointNetAModule, PointNetFPModule, Attention, Swish
File "/home//MyProjects/PVD/train_generation.py", line 11, in
from model.pvcnn_generation import PVCNN2Base

Problem in installing dependencies

Hi, thank you for sharing your code. I have some problems in running the code. My system is Windows 10.

Why only use extra features in the last fp module

pvcnn_generation.py
line190

only use extra features in the last fp module

sa_in_channels[0] = extra_feature_channels

EMD doesn't match with PointFlow's

Hi,

I used your EMD code and PointFlow's to compute and find the two do not match. Yours is approximately 10 times less than PointFlow's. Could you please check this?

Airplane:
Yours
{'1-NN-CD-acc': 0.7259259223937988,
'1-NN-CD-acc_f': 0.6370370388031006,
'1-NN-CD-acc_t': 0.8148148059844971,
'1-NN-EMD-acc': 0.614814817905426,
'1-NN-EMD-acc_f': 0.5629629492759705,
'1-NN-EMD-acc_t': 0.6666666865348816,
'lgan_cov-CD': 0.4962962865829468,
'lgan_cov-EMD': 0.47654321789741516,
'lgan_mmd-CD': 0.00022858072770759463,
'lgan_mmd-EMD': 0.0035688027273863554,
'lgan_mmd_smp-CD': 0.0007089844439178705,
'lgan_mmd_smp-EMD': 0.006884903181344271}
'JSD: 0.04573863398532296'

PointFlow's
{'1-NN-CD-acc': 0.7259259223937988,
'1-NN-CD-acc_f': 0.6370370388031006,
'1-NN-CD-acc_t': 0.8148148059844971,
'1-NN-EMD-acc': 0.6740740537643433,
'1-NN-EMD-acc_f': 0.6320987939834595,
'1-NN-EMD-acc_t': 0.7160493731498718,
'lgan_cov-CD': 0.4962962865829468,
'lgan_cov-EMD': 0.5185185074806213,
'lgan_mmd-CD': 0.00022858072770759463,
'lgan_mmd-EMD': 0.03101278468966484,
'lgan_mmd_smp-CD': 0.0007089844439178705,
'lgan_mmd_smp-EMD': 0.04470111057162285}
'JSD: 0.04573863398532296'

Hi, can you provide more checkpoints about partnet dataset ? thanks

How do you visualize the point cloud in the paper?

Hi,

Thanks for your nice work!
May I ask how do you visualize the point cloud in the paper?

Best

Request for PartNet model

Could you please release the testing script and the pre-trained model for PartNet?
Thanks a lot!

why need the noise init

thanks for you excellent work. I have a question here, for the cases of image generation using DDPM, no noise init is provided. so why we need the noise init in the code ?

How many epochs were trained?

Hi,
Thanks for your excellent work!
I am curious that how many epochs the model had been trained to produce the results in the paper?

Questions about metrics

Hi! Thanks for your wonderful work.

I want to ask a question about the metrics. I read your code in test_generation.py and find that the metrics are calculated between generated sample and test sample read from dataset. In your diffusion model, generated samples are random generated and it may differ in each running result. So when calculating the Chamfer Distance( calculate the distance between generated samples and test samples), it may cause a doubt result. I want to know how to guarantee a reliable result.

Best.

About Visualization

We are really impressed by your wonderful work especially the visualization in your experiments. Could you please share the codes to visualize point cloud with 3D balls or give us some tips on how to make point cloud with 3D rendering.

What's the point using first 10,000 points in training set for training, and last 5,000 points in test set for evaluation?