Datasets
Standard Dataset
Walnuts

- Citation Author(s):
- Submitted by:
- Nadja Gruber
- Last updated:
- Mon, 03/24/2025 - 13:47
- DOI:
- 10.21227/8rze-np45
- License:
- Categories:
- Keywords:
Abstract
Walnut and Heart CT Data corresponding to Noisier2Inverse consist of high-resolution computed tomography (CT) scans used for evaluating deep learning-based image reconstruction under severe noise conditions. The dataset includes walnut CT scans from controlled experimental settings and clinical cardiac CT images. The Walnut data stems from this source: https://paperswithcode.com/dataset/cbct-walnut, and the Heart CT data is processed in python before, and is provided in .pt format. The origintal image stem from https://www.kaggle.com/datasets/abbymorgan/heart-ct. The exact preprocessing and also how the noise is put on the data can be found on our Github https://github.com/Nadja1611/Noisier2Inverse-Joint-Denoising-and-Reconstruction-of-correlated-noise
There are the folders: train, test an test_paper, while test was used as validation set during training, while test_paper contains images used in results of paper