Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation

TL;DR

This paper introduces a simple, single-model semi-supervised approach for unsupervised domain adaptation in monocular depth estimation, achieving state-of-the-art results on standard benchmarks by enforcing consistency across augmented views.

Contribution

It formulates domain adaptation as a consistency-based semi-supervised learning problem and proposes a pairwise loss function that improves depth estimation without complex training protocols.

Findings

Achieves state-of-the-art results on KITTI and NYUv2 benchmarks.

Requires only training a single model, simplifying the process.

Demonstrates effectiveness through ablation studies.

Abstract

In monocular depth estimation, unsupervised domain adaptation has recently been explored to relax the dependence on large annotated image-based depth datasets. However, this comes at the cost of training multiple models or requiring complex training protocols. We formulate unsupervised domain adaptation for monocular depth estimation as a consistency-based semi-supervised learning problem by assuming access only to the source domain ground truth labels. To this end, we introduce a pairwise loss function that regularises predictions on the source domain while enforcing perturbation consistency across multiple augmented views of the unlabelled target samples. Importantly, our approach is simple and effective, requiring only training of a single model in contrast to the prior work. In our experiments, we rely on the standard depth estimation benchmarks KITTI and NYUv2 to demonstrate state-of-the-art results compared to related approaches. Furthermore, we analyse the simplicity and effectiveness of our approach in a series of ablation studies. The code is available at \url{https://github.com/AmirMaEl/SemiSupMDE}.