360D: A dataset and baseline for dense depth estimation from 360 images

Abstract:


We present a baseline for 360o dense depth estimation from a single spherical panorama. We circumvent the unavailability of coupled 360o color and depth image datasets by rendering a high quality 360o dataset from existing 3D datasets. We then train a CNN designed speci_cally for 360o content in a supervised manner, in order to predict a 360o depth map from a single omnidirectional image in equirectangular format. Quantitative and qualitative results show the need for training directly in 360o instead of relying on traditional 2D CNNs.


  • A. Karakottas, N. Zioulis, D. Zarpalas, P. Daras, "360D: A dataset and baseline for dense depth estimation from 360 images", 1st Workshop on 360o Perception and Interaction, European Conference on Computer Vision (ECCV) , Munich, Germany, 8 – 14 September 2018

  • Full document available here.
    Contact Information

    Dr. Petros Daras, Principal Researcher Grade Α
    1st km Thermi – Panorama, 57001, Thessaloniki, Greece
    P.O.Box: 60361
    Tel.: +30 2310 464160 (ext. 156)
    Fax: +30 2310 464164
    Email: daras@iti.gr