Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes
(2023) 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 In Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 p.1-10- Abstract
This paper presents a neural network based semantic plane detection method utilizing polygon representations. The method can for example be used to solve room layout estimations tasks and is built on, combines and further develops several different modules from previous research. The network takes an RGB image and estimates a wireframe as well as a feature space using an hourglass backbone. From these, line and junction features are sampled. The lines and junctions are then represented as an undirected graph, from which polygon representations of the sought planes are obtained. Two different methods for this last step are investigated, where the most promising method is built on a heterogeneous graph transformer. The final output is in... (More)
This paper presents a neural network based semantic plane detection method utilizing polygon representations. The method can for example be used to solve room layout estimations tasks and is built on, combines and further develops several different modules from previous research. The network takes an RGB image and estimates a wireframe as well as a feature space using an hourglass backbone. From these, line and junction features are sampled. The lines and junctions are then represented as an undirected graph, from which polygon representations of the sought planes are obtained. Two different methods for this last step are investigated, where the most promising method is built on a heterogeneous graph transformer. The final output is in all cases a projection of the semantic planes in 2D. The methods are evaluated on the Structured3D dataset and we investigate the performance both using sampled and estimated wireframes. The experiments show the potential of the graph-based method by outperforming state of the art methods in Room Layout estimation in the 2D metrics using synthetic wireframe detections.
(Less)
- author
- Gillsjö, David LU ; Flood, Gabrielle LU and Åström, Kalle LU
- organization
-
- Computer Vision and Machine Learning (research group)
- LTH Profile Area: AI and Digitalization
- eSSENCE: The e-Science Collaboration
- Mathematics (Faculty of Engineering)
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- LU Profile Area: Nature-based future solutions
- LU Profile Area: Light and Materials
- LU Profile Area: Proactive Ageing
- LU Profile Area: Natural and Artificial Cognition
- LTH Profile Area: Engineering Health
- Stroke Imaging Research group (research group)
- Mathematical Imaging Group (research group)
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Graph Neural Network, Polygon detection, Room Layout Estimation, Wireframe Parsing
- host publication
- Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
- series title
- Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
- pages
- 10 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
- conference location
- Paris, France
- conference dates
- 2023-10-02 - 2023-10-06
- external identifiers
-
- scopus:85182943502
- ISBN
- 9798350307443
- DOI
- 10.1109/ICCVW60793.2023.00007
- language
- English
- LU publication?
- yes
- id
- 4e1c0ecf-03ca-4e1d-812a-6a17c85a3b61
- date added to LUP
- 2024-02-16 15:16:25
- date last changed
- 2024-02-16 15:17:34
@inproceedings{4e1c0ecf-03ca-4e1d-812a-6a17c85a3b61, abstract = {{<p>This paper presents a neural network based semantic plane detection method utilizing polygon representations. The method can for example be used to solve room layout estimations tasks and is built on, combines and further develops several different modules from previous research. The network takes an RGB image and estimates a wireframe as well as a feature space using an hourglass backbone. From these, line and junction features are sampled. The lines and junctions are then represented as an undirected graph, from which polygon representations of the sought planes are obtained. Two different methods for this last step are investigated, where the most promising method is built on a heterogeneous graph transformer. The final output is in all cases a projection of the semantic planes in 2D. The methods are evaluated on the Structured3D dataset and we investigate the performance both using sampled and estimated wireframes. The experiments show the potential of the graph-based method by outperforming state of the art methods in Room Layout estimation in the 2D metrics using synthetic wireframe detections.</p>}}, author = {{Gillsjö, David and Flood, Gabrielle and Åström, Kalle}}, booktitle = {{Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023}}, isbn = {{9798350307443}}, keywords = {{Graph Neural Network; Polygon detection; Room Layout Estimation; Wireframe Parsing}}, language = {{eng}}, pages = {{1--10}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023}}, title = {{Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes}}, url = {{http://dx.doi.org/10.1109/ICCVW60793.2023.00007}}, doi = {{10.1109/ICCVW60793.2023.00007}}, year = {{2023}}, }