Please use this identifier to cite or link to this item:
https://dspace.crs4.it/jspui/handle/1138/32
Title: | SliceNet: deep dense depth estimation from a single indoor panorama using a slice-based representation | Authors: | Pintore, Giovanni Agus, Marco Almansa, Eva Schneider, Jens Gobbetti, Enrico |
Affiliations: | CRS4 HBKU CRS4 HBKU CRS4 |
Keywords: | visual computing;indoor reconstruction;indoor panorama | Issue Date: | Jun-2021 | Project: | Advanced Visual and Geometric Computing for 3D Capture, Display, and Fabrication VIGECLAB |
Related Publication(s): | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) | Start page: | 11536 | End page: | 11545 | Abstract: | We introduce a novel deep neural network to estimate a depth map from a single monocular indoor panorama. The network directly works on the equirectangular projection, exploiting the properties of indoor 360-degree images. Starting from the fact that gravity plays an important role in the design and construction of man-made indoor scenes, we propose a compact representation of the scene into vertical slices of the sphere, and we exploit long- and short-term relationships among slices to recover the equirectangular depth map. Our design makes it possible to maintain high-resolution information in the extracted features even with a deep network. The experimental results demonstrate that our method outperforms current state-of-the-art solutions in prediction accuracy, particularly for real-world data. |
URI: | https://dspace.crs4.it/jspui/handle/1138/32 |
Appears in Collections: | CRS4 publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
cvpr2021-slicenet.pdf | Green OA copy | 4,38 MB | Adobe PDF | View/Open |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.