Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs

TL;DR

This paper introduces an unsupervised method for single-image depth synthesis using cycle-consistent Wasserstein GANs, enabling depth estimation without paired data, suitable for real-world autonomous systems.

Contribution

The study proposes a novel unsupervised approach employing cycle-consistent Wasserstein GANs for single-image depth synthesis, eliminating the need for paired training data.

Findings

Effective depth synthesis on industrial and NYU datasets

Comparable or superior results to supervised methods

Potential for real-world autonomous applications

Abstract

Real-time estimation of actual environment depth is an essential module for various autonomous system tasks such as localization, obstacle detection and pose estimation. During the last decade of machine learning, extensive deployment of deep learning methods to computer vision tasks yielded successful approaches for realistic depth synthesis out of a simple RGB modality. While most of these models rest on paired depth data or availability of video sequences and stereo images, there is a lack of methods facing single-image depth synthesis in an unsupervised manner. Therefore, in this study, latest advancements in the field of generative neural networks are leveraged to fully unsupervised single-image depth synthesis. To be more exact, two cycle-consistent generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance. To ensure plausibility of the proposed method, we apply the models to a self acquised industrial data set as well as to the renown NYU Depth v2 data set, which allows comparison with existing approaches. The observed success in this study suggests high potential for unpaired single-image depth estimation in real world applications.