EndoAbS Dataset

The <strong>EndoAbS Dataset</strong> (Endoscopic Abdominal Stereo Images Dataset) aims to provide to the computer assisted surgery community a dataset for the validation of 3D reconstruction algorithms.<br> It is composed of:<br> - 120 pair of endoscopic stereo images of abdominal organs (liver, kidneys, spleen);<br> - corresponding ground truth in left-camera reference frame, generated using a laser scanner;<br> - camera calibration parameters; The images were captured under different conditions:<br> - different light levels;<br> - presence of smoke; <br> - two phantom-endoscope distances (~5cm or ~10cm);<br> <br> If you use this dataset, please cite:<br> <br> Penza, V., Ciullo, A. S., Moccia, S., Mattos, L. S., &amp; De Momi, E. (2018). EndoAbS dataset: Endoscopic abdominal stereo image dataset for benchmarking 3D stereo reconstruction algorithms. <em>The International Journal of Medical Robotics and Computer Assisted Surgery</em>, e1926. For further information, please contact [e-mail]