The goal of this project is to develop a pipeline that can do online 3D reconstruction of small scale obejects, only using visual data from RGB-D camera. While some commercial 3D scanner can provide ...

A self-supervised Masked Autoencoder for 3D LiDAR point clouds, implemented in PyTorch and trained on the KITTI odometry dataset. Inspired by Point-MAE (Pang et al., 2022), this project learns rich 3D ...