Unsupervised Monocular Depth Estimation in Highly Complex Environments

TL;DR

This paper introduces an unsupervised monocular depth estimation framework that employs domain adaptation to effectively estimate depth in complex environments like night and rainy scenes, overcoming photometric consistency challenges.

Contribution

It proposes a novel image transfer-based domain adaptation method that enables depth models trained on daytime data to perform well in highly complex scenarios.

Findings

Effective depth estimation in night and rainy scenes

Improved robustness through image transfer quality evaluation

Enhanced depth accuracy via feature and output space constraints

Abstract

With the development of computational intelligence algorithms, unsupervised monocular depth and pose estimation framework, which is driven by warped photometric consistency, has shown great performance in the daytime scenario. While in some challenging environments, like night and rainy night, the essential photometric consistency hypothesis is untenable because of the complex lighting and reflection, so that the above unsupervised framework cannot be directly applied to these complex scenarios. In this paper, we investigate the problem of unsupervised monocular depth estimation in highly complex scenarios and address this challenging problem by adopting an image transfer-based domain adaptation framework. We adapt the depth model trained on day-time scenarios to be applicable to night-time scenarios, and constraints on both feature space and output space promote the framework to learn the key features for depth decoding. Meanwhile, we further tackle the effects of unstable image transfer quality on domain adaptation, and an image adaptation approach is proposed to evaluate the quality of transferred images and re-weight the corresponding losses, so as to improve the performance of the adapted depth model. Extensive experiments show the effectiveness of the proposed unsupervised framework in estimating the dense depth map from highly complex images.