FleX-ray Walnut CBCT Collection (CWI)
42 walnuts scanned on three different orbits each, so that artefact-free reference volumes can be computed from the combined views and used as supervised-learning ground truth. Worth noting that this is not another single-object phantom: the intent is natural variability across a class of objects. Ships the complete pipeline - raw projections, scanning geometry, pre-processing and reconstruction scripts (open software) and the reconstructed volumes - which makes it usable for high cone-angle artefact reduction, sparse and limited-angle reconstruction, super-resolution and segmentation alike. Split across six Zenodo deposits covering Samples 1-42.
| Type | Dataset |
|---|---|
| Data | Projection + image |
| Modality | cone-beam micro-CT |
| Tasks | reconstruction, limited-angle, sparse-view, cone-beam, segmentation |
| Licence (of the dataset) | CC BY 4.0 |
| Official page | https://zenodo.org/records/2686726 |
| Homepage | https://doi.org/10.1038/s41597-019-0235-y |
Related topics
Topic pages that list this entry among their datasets and benchmarks.
- Sparse-View CT (157)
- Limited-Angle Tomography (46)
- Cone-Beam CT (77)
- Implicit Neural Representations (25)
Guides
Guides that compare this entry with the alternatives.
- Sparse-View CT Reconstruction: Methods, Datasets and Where to Start
- How to Choose a CT Reconstruction Dataset
Everything on this page comes from the directory record (last content update 2026-10-16). Licence terms and access conditions can change: check the official page before you download or redistribute the data.