KPConv-PyTorch icon indicating copy to clipboard operation
KPConv-PyTorch copied to clipboard

Kernel Point Convolution implemented in PyTorch

Results 106 KPConv-PyTorch issues
Sort by recently updated
recently updated
newest added

Hello, thank you very much for your code. My sincere respect to you! I want to replace the s3dis data set with my data set, and I want to use...

Hi, First of all I must say that I enjoyed reading your paper, and the supplied GitHub is very useful - thanks for that! I have a question regarding the...

Hi Thomas, Thank you for sharing the code. I tried to install the package but I have had a problem compiling the C++ extension modules for python. Once I click...

Thank you for sharing this project; I'm finding the code to be clear and well commented, which makes it easier to understand. One parameter I don't undestand though is why...

` if self.config.in_features_dim == 1: pass elif self.config.in_features_dim == 4: stacked_features = np.hstack((stacked_features, features[:, :3])) elif self.config.in_features_dim == 5: stacked_features = np.hstack((stacked_features, features)) elif self.config.in_features_dim == 7: stacked_features = np.hstack((stacked_features,...

Occasionally, during calibration, I encounter the following error: "It seems this dataset only containes empty input spheres" ). his issue appears with datasets like NPM3D, S3DIS, and Toronto3D. After some...

Hi, Hugues Thank you very much for your great codes. I have one question on implementation with the S3DIS datasets (on windows). Firstly, I use visualization APP to render the...

Hello, HuguesTHOMAS! When I try to use the function cpp_neighbors.batch_query() function in some other scenes, I find a failure case that when the code goes into this function, the code...

Hello, I've experimented with the NPM3D dataset. The training went well, but when I tried testing the model with test_models.py, the test seems to never stop. Currently, it's at 1481...

Thank you for your amazing work! @HuguesTHOMAS May i ask is there an available pretrained model or test results for Toronto3D?