Scan2CAD is an alignment dataset based on 1506 ScanNet scans with 97607 annotated keypoints pairs between 14225 (3049 unique) CAD models from ShapeNet and their counterpart objects in the scans. The top 3 annotated model classes are chairs, tables and cabinets which arises due to the nature of indoor scenes in ScanNet. The number of objects aligned per scene ranges from 1 to 40 with an average of 9.3.
Additionally, all ShapeNet CAD models used in the Scan2CAD dataset are annotated with their rotational symmetries: either none, 2-fold, 4-fold or infinite rotational symmetries around a canonical axis of the object.
Source: Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
Image Source: Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
Variants: Scan2CAD
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| 3D Reconstruction | Scan2CAD | Scan2CAD: Learning CAD Model Alignment … | 2018-11-27 |
| 3D Reconstruction | 3DMatch | 3DMatch: Learning Local Geometric Descriptors … | 2016-03-27 |
Recent papers with results on this dataset: