Learning-based partial point cloud completion system using kernel points convolution
This project implements a Kernel Point Convolution pipeline for edge detection in 3D point clouds, developed as part of the ABC Challenge. It aims to automatically identify edge points in 3D models of manufactured objects by combining geometric features (coordinates, normals, and multi-scale descriptors) within a U-Net–style KPConv architecture.
Add a description, image, and links to the kernel-points-convolution topic page so that developers can more easily learn about it.
To associate your repository with the kernel-points-convolution topic, visit your repo's landing page and select "manage topics."