Please use this identifier to cite or link to this item:
Title: AtlantaNet: Inferring the 3D Indoor Layout from a Single 360 Image beyond the Manhattan World Assumption
Authors: Pintore, Giovanni 
Agus, Marco 
Gobbetti, Enrico 
Affiliations: CRS4 
Keywords: 3D floor plan recovery;panoramic images;360 images;data-driven reconstruction;structured indoor reconstruction;indoor panorama;room layout estimation;holistic scene reconstruction;visual computing
Issue Date: Nov-2020
Publisher: Springer
Project: Advanced Visual and Geometric Computing for 3D Capture, Display, and Fabrication 
Related Publication(s): Computer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII
Journal: LNCS 
Volume: 12353
Start page: 432
End page: 448
Conference: ECCV 2020 
We introduce a novel end-to-end approach to predict a 3D room layout from a single panoramic image. Compared to recent state-of-the-art works, our method is not limited to Manhattan World environments, and can reconstruct rooms bounded by vertical walls that do not form right angles or are curved - i.e., Atlanta World models. In our approach, we project the original gravity-aligned panoramic image on two horizontal planes, one above and one below the camera. This representation encodes all the information needed to recover the Atlanta World 3D bounding surfaces of the room in the form of a 2D room footprint on the floor plan and a room height. To predict the 3D layout, we propose an encoder-decoder neural network architecture, leveraging Recurrent Neural Networks (RNNs) to capture long-range geometric patterns, and exploiting a customized training strategy based on domain-specific knowledge. The experimental results demonstrate that our method outperforms state-of-the-art solutions in prediction accuracy, in particular in cases of complex wall layouts or curved wall footprints.
DOI: 10.1007/978-3-030-58598-3_26
Rights: info:eu-repo/semantics/openAccess
Appears in Collections:CRS4 publications

Files in This Item:
File Description SizeFormat
eccv2020-atlantanet.pdfAcceoted version10,45 MBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Nov 11, 2020

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.