AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

03/05/2018
by   Jogendra Nath Kundu, et al.
0

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 semi-supervised setting.

READ FULL TEXT

page 1

page 4

page 7

01/19/2020

FIS-Nets: Full-image Supervised Networks for Monocular Depth Estimation

This paper addresses the importance of full-image supervision for monocu...
09/24/2021

Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation

Depth estimation from monocular images is an important task in localizat...
07/30/2022

Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation

Monocular depth estimation (MDE) has attracted intense study due to its ...
04/12/2021

Domain Adaptive Monocular Depth Estimation With Semantic Information

The advent of deep learning has brought an impressive advance to monocul...
03/30/2020

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

In the current monocular depth research, the dominant approach is to emp...
03/26/2022

Learn to Adapt for Monocular Depth Estimation

Monocular depth estimation is one of the fundamental tasks in environmen...
07/28/2021

Unsupervised Monocular Depth Estimation in Highly Complex Environments

Previous unsupervised monocular depth estimation methods mainly focus on...