On the Benefit of Adversarial Training for Monocular Depth Estimation

TL;DR

This paper investigates the impact of adversarial training on monocular depth estimation, finding it beneficial only with less constrained reconstruction losses, and achieves state-of-the-art results with specific training strategies.

Contribution

It provides a comprehensive evaluation of adversarial training methods in monocular depth estimation and identifies conditions under which they improve performance.

Findings

Adversarial training benefits are limited to less constrained reconstruction losses.

Non-adversarial methods outperform GAN-based methods with constrained losses.

State-of-the-art results are achieved using batch normalization and multi-scale outputs.

Abstract

In this paper we address the benefit of adding adversarial training to the task of monocular depth estimation. A model can be trained in a self-supervised setting on stereo pairs of images, where depth (disparities) are an intermediate result in a right-to-left image reconstruction pipeline. For the quality of the image reconstruction and disparity prediction, a combination of different losses is used, including L1 image reconstruction losses and left-right disparity smoothness. These are local pixel-wise losses, while depth prediction requires global consistency. Therefore, we extend the self-supervised network to become a Generative Adversarial Network (GAN), by including a discriminator which should tell apart reconstructed (fake) images from real images. We evaluate Vanilla GANs, LSGANs and Wasserstein GANs in combination with different pixel-wise reconstruction losses. Based on extensive experimental evaluation, we conclude that adversarial training is beneficial if and only if the reconstruction loss is not too constrained. Even though adversarial training seems promising because it promotes global consistency, non-adversarial training outperforms (or is on par with) any method trained with a GAN when a constrained reconstruction loss is used in combination with batch normalisation. Based on the insights of our experimental evaluation we obtain state-of-the art monocular depth estimation results by using batch normalisation and different output scales.