There is a newer version of the record available.

Published September 19, 2025 | Version v2
Dataset Open

KidneyDepth: A Synthetic Kidney Dataset for Metric Depth Estimation in Ureteroscopy

Authors/Creators

  • 1. ROR icon Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
  • 2. ROR icon Karlsruhe Institute of Technology
  • 3. ROR icon University of Freiburg

Description

KidneyDepth is a dataset composed by synthetic ureteroscopic images generated by BlenderProc and real ureteroscopic images. The objectives of this dataset are to generate ground truth maps for fine-tuning and evaluating metric depth estimation models (KidneyDepthMetric), to visually evaluate them on real endoscopic kidney images (KidneyDepthfURS), and to evaluate the estimated trajectories of a SLAM system (KidneyDepthSLAM).

Files

README.md

Files (49.1 GB)

Name Size
md5:65eed9cb519cc206a4c1cdc9ac2f07c4
49.1 GB Download
md5:9ae8df8c122f129ea63a649edd2972ce
4.3 kB Preview Download