Mechanical Part Point Cloud Completion Dataset

This dataset consists of 2,000 mechanical part samples collected using high-precision laser scanning. It is designed for point cloud completion tasks and can also support multi-modal learning if applicable.Dataset StructureThe dataset is organized into three subsets with the following split:<b>Training</b>: 85%<b>Validation</b>: 5%<b>Testing</b>: 10%Each subset contains three folders:<pre><pre>machine_part_point_cloud_dataset/<br>├── train/<br>│ ├── complete/ # Ground truth complete point clouds (.npy)<br>│ ├── incomplete/ # Incomplete point clouds (.npy)<br>│ └── rgb/ # Contour/rgb images (.npg)<br>├── val/<br>│ ├── complete/<br>│ ├── incomplete/<br>│ └── rgb/<br>└── test/<br> ├── complete/<br> ├── incomplete/<br> └── rgb/<br></pre></pre>Data Format<code>complete/</code>: Contains the complete point cloud of each sample in <code>.npy</code> format. Each file stores a NumPy array representing the full geometry of a mechanical part.<code>incomplete/</code>: Contains partial point clouds obtained from real-world occlusion and viewpoint limitations. Also in <code>.npy</code> format.<code>rgb/</code>: Contains <code>.npg</code> format files representing the 2D contour or appearance information of each part. These can serve as auxiliary input for multi-modal learning frameworks.ApplicationsThis dataset is suitable for tasks such as:3D point cloud completionMulti-modal 3D reconstructionLearning shape priors for mechanical partsPlease ensure your model correctly handles <code>.npy</code> and optionally <code>.npg</code> formats if using multi-modal inputs.