Semantic Room Wireframe Detection from a Single View
(2022) 26TH International Conference on Pattern Recognition, 2022 p.1886-1893- Abstract
- Reconstruction of indoor surfaces with limited texture information or with repeated textures, a situation common in walls and ceilings, may be difficult with a monocular Structure from Motion system. We propose a Semantic Room Wireframe Detection task to predict a Semantic Wireframe from a single perspective image. Such predictions may be used with shape priors to estimate the Room Layout and aid reconstruction. To train and test the proposed algorithm we create a new set of annotations from the simulated Structured3D dataset. We show qualitatively that the SRW-Net handles complex room geometries better than previous Room Layout Estimation algorithms while quantitatively out-performing the baseline in non-semantic Wireframe Detection.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/9852dc4e-c152-4a04-8ecd-dc8cf4b751f3
- author
- Gillsjö, David LU ; Flood, Gabrielle LU and Åström, Kalle LU
- organization
-
- Mathematics (Faculty of Engineering)
- eSSENCE: The e-Science Collaboration
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- LTH Profile Area: AI and Digitalization
- Stroke Imaging Research group (research group)
- Mathematical Imaging Group (research group)
- LTH Profile Area: Engineering Health
- publishing date
- 2022-08-25
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 26th International Conference on Pattern Recognition, 2022
- pages
- 1886 - 1893
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 26TH International Conference on Pattern Recognition, 2022
- conference location
- Montreal, Canada
- conference dates
- 2022-08-21 - 2022-08-25
- external identifiers
-
- scopus:85143639759
- ISBN
- 978-1-6654-9062-7
- 978-1-6654-9063-4
- DOI
- 10.1109/ICPR56361.2022.9956252
- project
- Semantic Structure from Motion
- language
- English
- LU publication?
- yes
- id
- 9852dc4e-c152-4a04-8ecd-dc8cf4b751f3
- alternative location
- https://arxiv.org/abs/2206.00491
- date added to LUP
- 2022-09-23 09:49:46
- date last changed
- 2024-07-10 00:55:25
@inproceedings{9852dc4e-c152-4a04-8ecd-dc8cf4b751f3, abstract = {{Reconstruction of indoor surfaces with limited texture information or with repeated textures, a situation common in walls and ceilings, may be difficult with a monocular Structure from Motion system. We propose a Semantic Room Wireframe Detection task to predict a Semantic Wireframe from a single perspective image. Such predictions may be used with shape priors to estimate the Room Layout and aid reconstruction. To train and test the proposed algorithm we create a new set of annotations from the simulated Structured3D dataset. We show qualitatively that the SRW-Net handles complex room geometries better than previous Room Layout Estimation algorithms while quantitatively out-performing the baseline in non-semantic Wireframe Detection.}}, author = {{Gillsjö, David and Flood, Gabrielle and Åström, Kalle}}, booktitle = {{26th International Conference on Pattern Recognition, 2022}}, isbn = {{978-1-6654-9062-7}}, language = {{eng}}, month = {{08}}, pages = {{1886--1893}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Semantic Room Wireframe Detection from a Single View}}, url = {{http://dx.doi.org/10.1109/ICPR56361.2022.9956252}}, doi = {{10.1109/ICPR56361.2022.9956252}}, year = {{2022}}, }