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

03/31/2021
by   Christoph Angermann, et al.
2

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.

READ FULL TEXT

page 3

page 11

page 13

page 22

page 23

page 24

research
01/28/2022

Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction

Real-time estimation of actual object depth is a module that is essentia...
research
04/13/2021

Single Image Depth Estimation: An Overview

We review solutions to the problem of depth estimation, arguably the mos...
research
01/14/2020

Single Image Depth Estimation Trained via Depth from Defocus Cues

Estimating depth from a single RGB images is a fundamental task in compu...
research
05/25/2019

Unsupervised Single Image Underwater Depth Estimation

Depth estimation from a single underwater image is one of the most chall...
research
04/04/2022

Monitoring social distancing with single image depth estimation

The recent pandemic emergency raised many challenges regarding the count...
research
05/02/2017

Out-of-focus: Learning Depth from Image Bokeh for Robotic Perception

In this project, we propose a novel approach for estimating depth from R...
research
06/10/2020

Real-time single image depth perception in the wild with handheld devices

Depth perception is paramount to tackle real-world problems, ranging fro...

Please sign up or login with your details

Forgot password? Click here to reset