AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

TL;DR

AdaDepth introduces an unsupervised domain adaptation method for monocular depth estimation that leverages adversarial learning and content consistency, effectively bridging the gap between synthetic and real-world scenes.

Contribution

It presents a novel unsupervised adaptation strategy specifically designed for pixel-wise depth regression, overcoming limitations of existing adversarial methods.

Findings

Achieves competitive results on depth estimation benchmarks.

Sets new state-of-the-art in semi-supervised depth estimation.

Effectively reduces domain shift between synthetic and real images.

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 semi-supervised setting.