Published October 17, 2019 | Version 1.0.0
Dataset Restricted

3D60 (Real Only - All Viewpoints)

  • 1. Centre for Research and Technology Hellas

Description

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.

3D60 is a collective dataset generated in the context of various 360o vision research works. It comprises multi-modal omnidirectional stereo renders of scenes from realistic and synthetic large-scale 3D datasets (Matterport3DStanford2D3D and SunCG).

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.

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.

Notes

Instructions, code and data splits available @ https://vcl3d.github.io/3D60/

Files

Restricted

The record is publicly accessible, but files are restricted to users with access.

Request access

If you would like to request access to these files, please fill out the form below.

You need to satisfy these conditions in order for this request to be accepted:

Please fill in the google form before performing the access request as indicated in https://vcl3d.github.io/3D60/ 

You are currently not logged in. Do you have an account? Log in here

Additional details

Related works

Is supplemented by
Dataset: 10.5281/zenodo.3407840 (DOI)
Dataset: 10.5281/zenodo.3407840 (DOI)
Dataset: 10.5281/zenodo.3407875 (DOI)

Funding

Hyper360 – Enriching 360 media with 3D storytelling and personalisation elements 761934
European Commission