There is a newer version of the record available.

Published January 8, 2024 | Version v1.0
Dataset Open

DREAMING - Diminished Reality for Emerging Applications in Medicine through Inpainting Dataset

  • 1. ROR icon Graz University of Technology
  • 2. ROR icon Essen University Hospital
  • 3. ROR icon University of Giessen
  • 4. ROR icon RWTH Aachen University

Description

Dataset for the DREAMING - Diminished Reality for Emerging Applications in Medicine through Inpainting Challenge

More information about the challenge can be found on the challenge website!

 

Timeline:

8th January 2024: First subset of training & validation data available.

22nd January 2024: Second subset of training & validation data available.

29th January 2024: Full training & validation data available.

 

Description:

The dataset was created using Unreal Engine 5.1, Unreal MetaHumans, 3D-COSI surgical instruments, POV-Surgery grasp generation and EasySynth.

Each scene contains:

  • "color": RGB input images
  • "gt": RGB ground truth images
  • "mask": Mask defining the area to be inpainted. White -> Background, Black -> Inpainting area
  • "CameraPoses.csv": Camera poses
  • "CameraRig.json": Camera intrinsics

 

Files

DREAMING_training_0000-0010.zip

Files (1.8 GB)

Name Size Download all
md5:b575374aee573e02d0e1e6f632b48586
1.8 GB Preview Download

Additional details

Funding

FWF Austrian Science Fund
enFaced 2.0 KLI 1044

Dates

Created
2024-01-08