Unsupervised Adversarial Depth Estimation using Cycled Generative Networks

TL;DR

This paper introduces an unsupervised adversarial deep learning method for stereo depth estimation using cycled generative networks, eliminating the need for costly ground truth annotations and achieving competitive results.

Contribution

It presents a novel cycle-consistent adversarial network architecture for unsupervised disparity map prediction in stereo images, advancing depth estimation without supervision.

Findings

Effective depth estimation on KITTI and Cityscapes datasets.

Competitive performance with state-of-the-art supervised methods.

Code and models publicly available for reproducibility.

Abstract

While recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance, costly ground truth annotations are required during training. To cope with this issue, in this paper we present a novel unsupervised deep learning approach for predicting depth maps and show that the depth estimation task can be effectively tackled within an adversarial learning framework. Specifically, we propose a deep generative network that learns to predict the correspondence field i.e. the disparity map between two image views in a calibrated stereo camera setting. The proposed architecture consists of two generative sub-networks jointly trained with adversarial learning for reconstructing the disparity map and organized in a cycle such as to provide mutual constraints and supervision to each other. Extensive experiments on the publicly available datasets KITTI and Cityscapes demonstrate the effectiveness of the proposed model and competitive results with state of the art methods. The code and trained model are available on https://github.com/andrea-pilzer/unsup-stereo-depthGAN.