DIODE (Dense Indoor/Outdoor DEpth) is a dataset that contains diverse high-resolution color images with accurate, dense, and far-range depth measurements. DIODE is the first public dataset to include RGBD images of indoor and outdoor scenes obtained with one sensor suite.
Refer to our homepage and technical report for more details.
- Training set, 81GB
- Validation set, 2.6 GB
DIODE data is organized hierarchically.
We have released RGB images, depth maps and depth validity masks:
RGB images (*.png
): RGB images with a resolution of 1024 ร 768.
Depth maps (*_depth.npy
): depth ground truth with the same resolution as the images.
Depth validity masks (*_depth_mask.npy
): validity masks where 1 denotes valid sensor return and 0 otherwise.
This development toolkit contains
- A json file that enumerates the data in DIODE. The layout of this file is explained in diode.py. It serves as the single point of reference during dataloading.
- A sample pytorch data loading module.
- A jupyter-notebook demo showcasing data loading, metadata querying and depth visualization.
@article{diode_dataset,
title={{DIODE}: {A} {D}ense {I}ndoor and {O}utdoor {DE}pth {D}ataset},
author={Igor Vasiljevic and Nick Kolkin and Shanyi Zhang and Ruotian Luo and
Haochen Wang and Falcon Z. Dai and Andrea F. Daniele and Mohammadreza Mostajabi and
Steven Basart and Matthew R. Walter and Gregory Shakhnarovich},
year = {2019}
journal={CoRR},
volume={abs/1908.00463},
year = {2019},
url={http://arxiv.org/abs/1908.00463}
}
If you have any questions, please contact us at [email protected].