Please use this identifier to cite or link to this item:
|Title:||SliceNet: deep dense depth estimation from a single indoor panorama using a slice-based representation||Authors:||Pintore, Giovanni
|Keywords:||visual computing;indoor reconstruction;indoor panorama||Issue Date:||Jun-2021||Project:||Advanced Visual and Geometric Computing for 3D Capture, Display, and Fabrication
|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.
|Appears in Collections:||CRS4 publications|
Show full item record
Files in This Item:
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.