DRIM Dataset

DRIM : Depth Restoration with Interference Mitigation
in Multiple LiDAR Depth Cameras

Kyung Hee University AIRLAB
Paper Github Dataset

Dataset Structure

  • This dataset provides Interference Affected Depth Data and Ground Truths from Multiple Intel Realsense L515 Systems.

Overview

Data

  • Raw Data (640 x 480)
    • Interference Unaffected Depth (1 channel, uint16)
    • Interference Unaffected RGB (3 channel, uint8)
    • Interference Affected Depth (1 channel, uint16)
    • Interference Affected RGB (3 channel, uint8)

  • Ground Truth (640 x 480)
    • Interference Artifact Mask (1 channel, uint8)
    • Sensor Artifact Mask (1 channel, uint8)
    • GT Depth Data (1 channel, uint16)

Objects (Directory Name)

  • We collect dataset using 20 different objects
    • robot arm (arm)
    • small blocks (blocks)
    • large blocks (blocks2)
    • books (books)
    • bottles (bottles)
    • boxes (boxes)
    • boxing gloves (boxing)
    • case (case)
    • chair (chair)
    • controller (controller)
    • cup (cup)
    • fire extinguisher (fire_ext)
    • photo frame (frame)
    • first aid kit (kit)
    • mouse (mouse)
    • paper bags (paper_bag)
    • paper cups (paper_cup)
    • shoes (shoes)
    • sign (sign)
    • tablet (tablet)

Data Directory


Dataset Directory Structure

Interference Affected Depth Data

License

The DRIM dataset is provided under the Open Database License (available here). This means that you are free to use, distribute, modify and create derivative works from this dataset, provided that you give appropriate credit to our work. In addition, any adapted version of this dataset that is used publicly must be released under the same licence, and any redistribution must remain open. When using the DRIM dataset, please ensure that you acknowledge our work by citing the referenced paper.

BibTeX

BibTex Code Here