zenodoopen
AssemblyNet: A Point Cloud Dataset for Predicting Part Directions in an Exploded Layout
<p>The AssemblyNet dataset contains 5420 samples of 512-point and 1024-point point clouds of mixed industrial assemblies and LEGO models.</p><p>The dataset contains classification and regression annotations for predicting which direction a part should be removed in to create an exploded layout.</p><p>Classification annotations use 26 classes representing 26 world space directions while regression annotations use the actual world space direction as X, Y, and Z values.</p>
ShareScore
32/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 8
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 0
- Engagement
- 4
ScienceDex for faculty
Your academic CV and NIH biosketch
Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.