thumbnail

SliceNet: deep dense depth estimation from a single indoor panorama using a slice-based representation

Giovanni Pintore, Marco Agus, Eva Almansa, Jens Schneider, and Enrico Gobbetti

2021

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.

Reference and download information

Giovanni Pintore, Marco Agus, Eva Almansa, Jens Schneider, and Enrico Gobbetti. SliceNet: deep dense depth estimation from a single indoor panorama using a slice-based representation. In Proc. CVPR, 2021. Selected as oral presentation. To appear.

Related multimedia productions

Bibtex citation record

@InProceedings{Pintore:2021:SDD,
    author = {Giovanni Pintore and Marco Agus and Eva Almansa and Jens Schneider and Enrico Gobbetti},
    title = {{SliceNet}: deep dense depth estimation from a single indoor panorama using a slice-based representation},
    booktitle = {Proc. CVPR},
    year = {2021},
    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. },
    note = {Selected as oral presentation. To appear},
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Pintore:2021:SDD'},
}