{"url":"/dataset/theostereo","name":"THEOStereo","full_name":null,"description_markdown":"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 *k_1 = 1* and *k_2 = k_3 = k_4 = k_5 = 0*. The length of the stereo camera's baseline was *0.3* AU (approx. *15* cm, not *30* cm!). Please do not forget to cite [1] if you use the dataset in your work. Thank you.\r\n\r\n## Structure of the Dataset\r\n\r\n```\r\n.\r\n├── README.md\r\n├── test\r\n│   ├── depth_exr_abs\r\n│   ├── img_stereo_webp\r\n│   └── img_webp\r\n├── train\r\n│   ├── depth_exr_abs\r\n│   ├── img_stereo_webp\r\n│   └── img_webp\r\n└── valid\r\n    ├── depth_exr_abs\r\n    ├── img_stereo_webp\r\n    └── img_webp\r\n```\r\n\r\nThe directory `depth_exr_abs` contain the depth maps given in meters. The depth reference to the image of the left camera. All images of the left camera are stored in the `img_webp`. The right camera's images can be found in `img_stereo_webp`.\r\n\r\n## License\r\n\r\nThis dataset is licensed under CC BY 4.0.  \r\nFor details, please visit <https://creativecommons.org/licenses/by/4.0/>.\r\n\r\n[![CC BY 4.0 Logo](https://mirrors.creativecommons.org/presskit/buttons/88x31/svg/by.svg)](https://creativecommons.org/licenses/by/4.0/)\r\n\r\n## Conference paper\r\nThe conference paper can be downloaded from [here](https://www.scitepress.org/Papers/2021/103248/103248.pdf).\r\n\r\n## BibTex\r\nIf you use the dataset in your work, we would kindly ask you to cite [1].\r\nYou might want to use the following BibTex entry:\r\n```bibtex\r\n@inproceedings{seuffert_study_2021,\r\n\taddress = {Online Conference},\r\n\ttitle = {A {Study} on the {Influence} of {Omnidirectional} {Distortion} on {CNN}-based {Stereo} {Vision}},\r\n\tisbn = {978-989-758-488-6},\r\n\tdoi = {10.5220/0010324808090816},\r\n\tbooktitle = {Proceedings of the 16th {International} {Joint} {Conference} on {Computer} {Vision}, {Imaging} and {Computer} {Graphics} {Theory} and {Applications}, {VISIGRAPP} 2021, {Volume} 5: {VISAPP}},\r\n\tpublisher = {SciTePress},\r\n\tauthor = {Seuffert, Julian Bruno and Perez Grassi, Ana Cecilia and Scheck, Tobias and Hirtz, Gangolf},\r\n\tyear = {2021},\r\n\tmonth = {2},\r\n\tpages = {809--816}\r\n}\r\n```\r\n\r\n## References\r\n[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.\r\n\r\n[2] J. Kannala, J. Heikkilä, and S. S. Brandt, “Geometric Camera Calibration,” in *Wiley Encyclopedia of Computer Science\r\nand Engineering*, B. W. Wah, Ed. Hoboken, NJ, USA: John Wiley & Sons, Inc., 2008.","description_withheld":null,"homepage":"https://www.tu-chemnitz.de/etit/dst/forschung/comp_vision/theostereo/index.php.en","introduced_date":"2021-02-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"A Study on the Influence of Omnidirectional Distortion on CNN-based Stereo Vision","first_author":null,"url":"https://www.scitepress.org/Link.aspx?doi=10.5220/0010324808090816"},"license":{"name":"CC BY 4.0","url":null},"modalities":[{"name":"RGB-D","url":"/datasets/modality/rgb-d"},{"name":"Stereo","url":"/datasets/modality/stereo"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"}],"variants":["THEOStereo"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}