21 datasets found

The dataset used in this paper for reconstructing sparsely sampled MRI data, including brain and knee images.

Fully sampled brain MRI data of 5 subjects acquired using a T2 CUBE sequence.

MRI scans appearance significantly depends on scanning protocols and, consequently, the data-collection institution. These variations between clinical sites result in dramatic...

MRI reconstruction dataset for unpaired training

MRI reconstruction dataset for unpaired training

The Stanford Fully Sampled 3D FSE Knees dataset is used for MRI reconstruction task. It contains 3D Cartesian proton-density knee scans of 20 healthy volunteers.

The Kirby21 dataset is used for Magnetic Resonance Imaging (MRI) reconstruction. It consists of 5460 slices of size 256x256 taken from 42 T1-weighted MPRAGE volumes.

The DIV2K dataset used for CT reconstruction.

The dataset used in this paper for MRI and CT reconstruction.

A cost-efficient, compact and easy to use active illumination camera for hyper-spectral reconstruction

The dataset used in this paper for dynamic MRI reconstruction.

The Neusdfusion dataset is a collection of 3D shapes, each represented as a point cloud. The dataset is used for 3D shape completion, reconstruction, and generation tasks.

WAIR-D is an open-source dataset named as Wireless AI Research Dataset, which is based on real-scenario maps and provides 3D ray-tracing parameters for wireless AI tasks.

The ImageInversion dataset is used to evaluate the reconstruction quality of different inversion methods.

The LERF dataset is a dataset for 3D scene understanding, where the goal is to reconstruct and segment 3D scenes. The dataset is constructed by capturing 360-degree views of 9...

The LoDoPaB-CT dataset is used to test the reconstruction methods. The dataset consists of 284,672 training samples and 10,000 test samples.

The dataset used in the paper for seismic data reconstruction

The dataset used in the paper for seismic data reconstruction

The fastmri dataset is used for MRI reconstruction. It contains fully sampled knee MR images and k-spaces from 1500 patients obtained from 1.5 and 3.0T scanners.

The dataset used in the paper for 3D head avatar reconstruction from monocular RGB videos.