Ινστιτούτο Τεχνολογιών Πληροφορικής και Επικοινωνιών

el en

Δημοσιεύσεις Ι.Π.ΤΗΛ.

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

We present a baseline for 360 dense depth estimation from a single spherical panorama. We circumvent the unavailability of coupled 360 color and depth image datasets by rendering a high quality 360 dataset from existing 3D datasets. We then train a CNN designed specifically for 360 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 360 instead of relying on traditional 2D CNNs.

Συνημμένα

Ινστιτούτο Τεχνολογιών Πληροφορικής και Επικοινωνιών

Τ.Θ.60361, 6ο χλμ Χαριλάου - Θέρμης, 57001, Θεσσαλονίκη
τηλ. 2311 257701-3 / fax. 2310 474128
email: