Please use this identifier to cite or link to this item:
Title: Improving outdoor plane estimation without manual supervision
Authors: Uzyıldırım, Furkan Eren
Özuysal, Mustafa
Keywords: Deep learning
Outdoor plane estimation
Transfer learning
Weakly supervised learning
Issue Date: Mar-2022
Publisher: Springer
Abstract: Recently, great progress has been made in the automatic detection and segmentation of planar regions from monocular images of indoor scenes. This has been achieved thanks to the development of convolutional neural network architectures for the task and the availability of large amounts of training data usually obtained with the help of active depth sensors. Unfortunately, it is much harder to obtain large image sets outdoors partly due to limited range of active sensors. Therefore, there is a need to develop techniques that transfer features learned from the indoor dataset to segmentation of outdoor images. We propose such an approach that does not require manual annotations on the outdoor datasets. Instead, we exploit a network trained on indoor images and an automatically reconstructed point cloud to estimate the training ground truth on the outdoor images in an energy minimization framework. We show that the resulting ground truth estimate is good enough to improve the network weights. Moreover, the process can be repeated multiple times to further improve plane detection and segmentation accuracy on monocular images of outdoor scenes.
ISSN: 1863-1703
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File SizeFormat 
Uzyıldırım-Özuysal2022.pdf1.61 MBAdobe PDFView/Open
Show full item record

CORE Recommender


checked on Feb 16, 2024


checked on Feb 17, 2024

Page view(s)

checked on Feb 19, 2024


checked on Feb 19, 2024

Google ScholarTM



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