differentiable-point-clouds
differentiable-point-clouds copied to clipboard
eldar
The reference implementation of "Unsupervised Learning of Shape and Pose with Differentiable Point Clouds"
thanks for your work, but there is one issue: FileNotFoundError: [Errno 2] No such file or directory: './final_reference_rotation.mat' hope you reply
I just want to utilize the "pointcloud_project_fast" function to project my pure point cloud to 2D image and calculate a loss with ground truth 2D image. But the output of...
Can you share the config you've used to train for smaller resolutions? Image size, voxel size, smoothing kernel size, gaussian std, dropout probability, number of iterations.
I tried training the model using the 02958343 data and found at least one training step had some issues: On step 655 some values were set to zero which led...
Hi! I'm currently trying to understand the source code for ```pointcloud_project_fast()``` in dpc/util/point_cloud.py. I am assuming that pc_perspective_transform() transforms the point cloud information from one camera to another camera. So...
Hi Eldar, Please could you post the versions of the python packages you used for this project? I've managed to train a model but I'm getting a few errors when...
Hello elder I want to create a new category of data，for example，“bike”. The ID is 02834778 **If I use the command ./download_train_data.sh 02834778 , it doesn't work.** So, the question...
I am trying "dpc" as a generator of point cloud for new category. To generate ground truth point clouds is obvious(dpc/densify/densify.py or chenhsuanlin/3D-point-cloud-generation's densify/densify.py). But I cannot find a way...
