On the Benefit of Adversarial Training for Monocular Depth Estimation

10/29/2019
by   Rick Groenendijk, et al.
11

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.

READ FULL TEXT

page 7

page 8

page 10

research
09/13/2016

Unsupervised Monocular Depth Estimation with Left-Right Consistency

Learning based methods have shown very promising results for the task of...
research
06/24/2021

Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes

Self-supervised deep learning methods have leveraged stereo images for t...
research
08/17/2022

Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency

Depth estimation is a crucial step for image-guided intervention in robo...
research
05/01/2019

Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation

The field of self-supervised monocular depth estimation has seen huge ad...
research
02/20/2023

Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinement

Monocular depth estimation plays a fundamental role in computer vision. ...
research
04/27/2020

Self-Supervised Attention Learning for Depth and Ego-motion Estimation

We address the problem of depth and ego-motion estimation from image seq...
research
05/11/2019

Monocular Depth Estimation with Directional Consistency by Deep Networks

As processing power has become more available, more human-like artificia...

Please sign up or login with your details

Forgot password? Click here to reset