AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

Kundu, Jogendra Nath and Uppala, Phani Krishna and Pahuja, Anuj and Babu, R Venkatesh (2018) AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation. In: 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), JUN 18-23, 2018, Salt Lake City, UT, pp. 2656-2665.

PDF Iee_Cvf_Con_Vis_Pat_Rec_CVPR_2656_2018.pdf - Published Version Restricted to Registered users only Download (529kB) | Request a copy

Abstract

Supervised deep learning methods have shown promising results for the task of monocular depth estimation; but acquiring ground truth is costly, and prone to noise as well as inaccuracies. While synthetic datasets have been used to circumvent above problems, the resultant models do not generalize well to natural scenes due to the inherent domain shift. Recent adversarial approaches for domain adaption have performed well in mitigating the differences between the source and target domains. But these methods are mostly limited to a classification setup and do not scale well for fully-convolutional architectures. In this work, we propose AdaDepth -an unsupervised domain adaptation strategy for the pixel-wise regression task of monocular depth estimation. The proposed approach is devoid of above limitations through a) adversarial learning and b) explicit imposition of content consistency on the adapted target representation. Our unsupervised approach performs competitively with other established approaches on depth estimation tasks and achieves state-of-the-art results in a semisupervised setting.

Item Type:	Conference Paper
Series.:	IEEE Conference on Computer Vision and Pattern Recognition
Publisher:	IEEE
Additional Information:	31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, JUN 18-23, 2018
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	27 Feb 2019 09:27
Last Modified:	27 Feb 2019 09:27
URI:	http://eprints.iisc.ac.in/id/eprint/61850

Actions (login required)

View Item