Sammanfattning

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.

Originalspråkengelska
Titel på värdpublikationProceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
FörlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Sidor1-10
Antal sidor10
ISBN (elektroniskt)9798350307443
DOI
StatusPublished - 2023
Evenemang2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 - Paris, Frankrike
Varaktighet: 2023 okt. 22023 okt. 6

Publikationsserier

NamnProceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023

Konferens

Konferens2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
Land/TerritoriumFrankrike
OrtParis
Period2023/10/022023/10/06

Ämnesklassifikation (UKÄ)

  • Datorseende och robotik (autonoma system)

Fingeravtryck

Utforska forskningsämnen för ”Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här