THEOStereo

THEOStereo is a dataset providing synthetic stereo image pairs and their corresponding scene depth and will be published along with [1]. All images follow the omnidirectional camera model. In total, there are 31,250 omnidirectional images pairs. The training set contains 25,000 image pairs. For validation and testing there are 3,125 image pairs, respectively. For each pair, there is a ground truth depth map describing the pixel-wise distance of the object along the left camera’s z-axis. The virtual omnidirectional cameras exhibit a FOV of 180 degrees and can be described using Kannala’s camera model [2]. The distortion parameters are k₁ = 1 and k₂ = k₃ = k₄ = k₅ = 0. The length of the stereo camera's baseline was 0.3 m 0.3 AU (approx. 15 cm)

Fig 1: Left camera image

Fig 2: Right camera image

Fig 3: Scene depth (ground truth)

Dataset Structure

.
├── README.md
├── test
│   ├── depth_exr_abs
│   ├── img_stereo_webp
│   └── img_webp
├── train
│   ├── depth_exr_abs
│   ├── img_stereo_webp
│   └── img_webp
└── valid
    ├── depth_exr_abs
    ├── img_stereo_webp
    └── img_webp

The directory depth_exr_abs contains the depth maps given in meters. The depth references to the image of the left camera. All images of the left camera are stored in img_webp. The right camera’s images can be found in img_stereo_webp.

License

This data set is licensed under a Creative Commons Attribution 4.0 International License.

Download

We recommend linux users to download the dataset with download.sh.
Alternatively, the dataset can be downloaded from our cloud and extracted manually.
The conference paper can be downloaded from here.

BibTeX

If you use the data set in your work, please don't forget to cite:

@inproceedings{seuffert_study_2021,
  address = {Online Conference},
  title = {A {Study} on the {Influence} of {Omnidirectional} {Distortion} on {CNN}-based {Stereo} {Vision}},
  isbn = {978-989-758-488-6},
  doi = {10.5220/0010324808090816},
  booktitle = {Proceedings of the 16th {International} {Joint} {Conference} on {Computer} {Vision}, {Imaging} and {Computer} {Graphics} {Theory} and {Applications}, {VISIGRAPP} 2021, {Volume} 5: {VISAPP}},
  publisher = {SciTePress},
  author = {Julian Bruno Seuffert and Ana Cecilia Perez Grassi and Tobias Scheck and Gangolf Hirtz},
  year = {2021},
  month = {2},
  pages = {809--816}
}

References

[1] J. B. Seuffert, A. C. Perez Grassi, T. Scheck, and G. Hirtz, “A Study on the Influence of Omnidirectional Distortion on CNN-based Stereo Vision,” in Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2021, Volume 5: VISAPP, Online Conference, Feb. 2021, pp. 809–816, doi: 10.5220/0010324808090816.

[2] J. Kannala, J. Heikkilä, and S. S. Brandt, “Geometric Camera Calibration,” in Wiley Encyclopedia of Computer Science and Engineering, B. W. Wah, Ed. Hoboken, NJ, USA: John Wiley & Sons, Inc., 2008.