3408441
doi
10.5281/zenodo.3408441
oai:zenodo.org:3408441
Karakottas, Antonis
Centre for Research and Technology Hellas
Zarpalas, Dimitrios
Centre for Research and Technology Hellas
Daras, Petros
Centre for Research and Technology Hellas
3D60 (Up Viewpoint)
Zioulis, Nikolaos
Centre for Research and Technology Hellas
doi:10.5281/zenodo.3407840
info:eu-repo/semantics/restrictedAccess
Spherical Panorama
360
Omnidirectional Image
Omnidirectional Stereo
Stereo Vision
Depth Estimation
Surface Estimation
Synthetic Data
Indoor Scenes
Scene Understanding
<p>Modern 3D vision advancements rely on data driven methods and thus, task specific annotated datasets. Especially for geometric inference tasks like depth and surface estimation, the collection of high quality data is very challenging, expensive and laborious. While considerable efforts have been made for traditional pinhole cameras, the same cannot be said for omnidirectional ones.</p>
<p><strong>3D60</strong> is a collective dataset generated in the context of various 360<sup>o</sup> vision research works. It comprises multi-modal omnidirectional stereo renders of scenes from realistic and synthetic large-scale 3D datasets (<em>Matterport3D</em>, <em>Stanford2D3D </em>and <em>SunCG</em>).</p>
<p>Our dataset fills a very important gap in data-driven spherical 3D vision and, more specifically, for the monocular and stereo dense depth and surface estimation tasks.</p>
<p>We originate by exploiting the efforts made in providing synthetic and real scanned 3D datasets of interior spaces and re-using them via ray-tracing in order to generate high quality, densely annotated spherical panoramas.</p>
Instructions, code and data splits available @ https://vcl3d.github.io/3D60/
Zenodo
2019-09-14
info:eu-repo/semantics/other
3408440
1.0.0
award_title=Enriching 360 media with 3D storytelling and personalisation elements; award_number=761934; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/761934; funder_id=00k4n6c32; funder_name=European Commission;
1579893905.48246
public
10.5281/zenodo.3407840
Is supplemented by
doi
10.5281/zenodo.3408440
isVersionOf
doi