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

Kernel Point Convolution implemented in PyTorch

Results 95 KPConv-PyTorch issues
Sort by recently updated
recently updated
newest added

Hi Dr.HuguesTHOMAS,I have a problem that has been bothering me for quite a long time, how to upsample in the decoding stage, as shown by the red line in the...

Hello Hugues, From what I understand from your thesis and the code, an input normalization strategy (for example unit sphere normalization) is not necessary because of the grid-based input subsampling...

Greate work in point cloud processing! I noticed that in your work, point cloud sampling and neighbor search is done before the data is fed into the network. I wonder...

Hello, I'm using your S3DIS point cloud segmentation code to train a custom dataset. I have several questions for you: First, the training set is all the `all_splits`? Second, if...

Hi THOMAS!thank you for your contribution! I met an error while running train_S3DIS as following: #### (pytorch) nky@nky-System-Product-Name:~/PycharmProjects/KPConv-pytorch$ python3 train_S3DIS.py Data Preparation **************** Preparing ply files Cloud Area_5 - Room...

Thank you Thomas for your nice work. I tried the classification code on my data with few classes (eight classes) by converting my data to ModelNet40 structure. The train and...

Good morning, I wanted to use this repo to perform a regression task on a bunch of pointclouds. My dataset then consists of pcd's with their regression score (between 0...

I downloaded the dataset again and completed the training and testing, but there was a problem. Open the Area_ 5. ply under the test result folder, the color displayed is...

Hi Hugues, I have one further question about the flexibility of your model and its V-RAM usage. [Question] I am encountering heavily varying V-RAM usage and even mid-training OOM on...

Hi @HuguesTHOMAS , I am trying to run semantic segmentation using your code on a custom dataset which is similar to S3DIS but has fewer number of classes. But the...