search

daipengwa / Neural-Point-Cloud-Rendering-via-Multi-Plane-Projection

(CVPR 2020) Neural Point Cloud Rendering via Multi-Plane Projection
MIT License
49 stars 9 forks source link

Is there any ways to process the cloud provided by users? #1

Closed evenhax closed 3 years ago

evenhax commented 3 years ago

For example, I want to use point cloud from Megadepth or built by myself. What should I do？

daipengwa commented 3 years ago

You should provide the point cloud, corresponding camera parameters, and RGB images for training. Our implementation is based on the scannet and matterport 3D, so you can provide the camera parameters like the two datasets, and ensure your point cloud is associated with your camera parameters. More information can be found in the ‘pre_processing/voxelizationaggregation*.py’.

evenhax commented 3 years ago

Thank you very much! I will have a try.