An implementation of the groundbreaking Point Cloud Upsampling Network (PU-Net) in PyTorch.

Developed by Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, and Pheng-Ann Heng, PU-Net offers a powerful solution for enhancing the resolution of point clouds.

Paper: [https://arxiv.org/pdf/1801.06761]

PU-Net introduces a novel neural network architecture specifically designed to upsample point clouds. It effectively increases the density of point clouds while preserving the detailed geometric structures, making it an essential tool for applications in 3D modeling, computer graphics, and computer vision.

Clone the repository and follow the instructions in the documentation to get started with PU-Net.

git clone https://github.com/yourusername/PU-Net.git
cd PU-Net

This implementation is part of a project for the Computer Engineering laboratory. We extend our gratitude to the original authors for their pioneering work and for making their research accessible to the community.