DIODE: A Dense Indoor and Outdoor DEpth Dataset

Authors: Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z. Dai, Andrea F. Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R. Walter, Gregory Shakhnarovich.
Affiliations: TTI-Chicago, University of Chicago, Beihang University.

Introduction

DIODE (Dense Indoor and Outdoor DEpth) is a dataset that contains diverse high-resolution color images with accurate, dense, far-range depth measurements. It is the first public dataset to include RGBD images of indoor and outdoor scenes obtained with one sensor suite. For more information, please refer to our technical report. More samples can be found in dataset sample gallery.

News

May 24th, 2020 : Due to the changed circumstances amid the COVID-19 pandemic, we have regrettably decided to cancel our workshop for CVPR2020. We hope to hold the workshop at a future venue, and will inform all interested parties as soon as we have a newly scheduled date. We apologize for any inconvenience.

Mar 31th, 2020 : Call for Paper is available now.

Dec 10th, 2019 : We will organize the CVPR 2020 Workshop "Frontiers of Monocular 3D Perception" together with Toyota Research Institute, more information will be updated in our Official Workshop Website.

DIODE Dataset

Dataset Download

We have released the train and validation splits of DIODE depth and DIODE normal, including RGB images, depth maps, depth validity masks and surface normal maps.

Download links:

DIODE Depth (RGB images, Depth maps and Depth validity masks):

Partition	Amazon Web Service	Baidu Cloud Storage	MD5 Hash
Train (81GB)	train.tar.gz	train.tar.gz	3a94632398fe1d002d89f11743f748b1
Validation (2.6GB)	val.tar.gz	val.tar.gz	5c895d09201b88973c8fe4552a67dd85

DIODE Normal (Normal maps only):

Partition	Amazon Web Service	Baidu Cloud Storage	MD5 Hash
Train (126GB)	train_normals.tar.gz	train_normals.tar.gz	9c0617ebe1eaf1928fdf3344e1c42aef
Validation (4.6GB)	val_normals.tar.gz	val_normals.tar.gz	323ccaf60abebdb59705dcd8b529d709

Data Enumeration Files: data_list.zip contains 4 (*.csv) files that list all instances in the train and val set of DIODE Dataset.

Dataset Layout

DIODE data is organized hierarchically. Detailed structure is shown as follows:

Description: A 'scene' usually corresponds to a somewhat compact location/vicinity, such as interior (or a single floor) of a building, surroundings of a landmark, neighborhood, etc. A 'scan' corresponds to a single data acquisition by the scanner, resulting in a set of crops, all taken from the same position. Multiple scans within the same scene may or may not have overlap in the physical points they capture; scans in distinct scenes will typically have no overlap. Note that we use the name of "indoors" and "outdoor" to keep the characters constant.

File Naming Conventions and Formats

The dataset consists of RGB images, depth maps, depth validity masks and surface normal maps. Their formats are as follows:

RGB images (*.png): RGB images with a resolution of 1024 × 768.

Depth maps (*_depth.npy): Depth ground truth with the same resolution as the images.

Depth masks (*_depth_mask.npy): Binary depth validity masks where 1 indicates valid sensor returns and 0 otherwise.

Surface normal maps (*_normal.npy): Surface normal vector ground truth with the same resolution as the images. Invalid normals are represented as (0,0,0).

Dataset Feature

Sensor Performance:

laser scanner

Diversity:

Example of Data Acquisition:

Dataset Statistics

Partitioning:

train	indoors	7 scenes	80 scans	8574 images
train	outdoor	12 scenes	100 scans	16884 images
val	indoors	3 scenes	10 scans	325 images
val	outdoor	3 scenes	10 scans	446 images
test	indoors	2 scenes	20 scans	753 images
test	outdoor	3 scenes	20 scans	876 images

Depth Distribution:

Legend:

Note: the max range of the depth color scheme is image-specific.

Baseline Performance

Here we provide the baseline performance of monocular depth estimation and surface normal estimation on the DIODE dataset. Please refer to Densedepth, Eigen et al. and our upcoming paper for more detail.

DIODE Development Toolkit

Please visit our official project repository for more information and DIODE development toolkit.
Devkit Link: diode-devkit

License

The DIODE dataset and the code is released using the MIT license.

Citation

If you use the DIODE dataset please cite:

@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},
  journal={CoRR},
  volume={abs/1908.00463},
  year={2019},
  url={http://arxiv.org/abs/1908.00463}
}

      

Acknowledgements

This research was in part sponsored by:

The Air Force Research Laboratory and DARPA under awards number FA8750-18-2-0126 and FA9550-18-1-0166.
The Robotics Consortium of the U.S. Army Research Laboratory under the Collaborative Technology Alliance Program Cooperative Agreement W911NF-10-2-0016.

Changelog

Nov 12th, 2019 : Baseline performance of surface normal estimation is released. DIODEv2 (upgraded version of DIODE with more locations and additional variety in weather and season) is around the corner.

Oct 17th, 2019 : DIODE surface normal data is released.

Sep 24th, 2019 : The previous statement about a bug in our rendering code turns out to be a false alarm.

Aug 30th, 2019 : Baseline performance of monocular depth estimation and v2 paper is released.

Aug 1st, 2019 : DIODE initial release.

Last updated: March 31th, 2020