A Novel Method for Estimating Monocular Depth Using Cycle GAN and Segmentation
Open Access
Abstract
Modern image processing techniques use three-dimensional (3D) images, which contain spatial information such as depth and scale, in addition to visual information. These images are indispensable in virtual reality, augmented reality (AR), and autonomous driving applications. We propose a novel method to estimate monocular depth using a cycle generative adversarial network (GAN) and segmentation. In this paper, we propose a method for estimating depth information by combining segmentation. It uses three processes: segmentation and depth estimation, adversarial loss calculations, and cycle consistency loss calculations. The cycle consistency loss calculation process evaluates the similarity of two images when they are restored to their original forms after being estimated separately from two adversarial losses. To evaluate the objective reliability of the proposed method, we compared our proposed method with other monocular depth estimation (MDE) methods using the NYU Depth Dataset V2. Our results show that the benchmark value for our proposed method is better than other methods. Therefore, we demonstrated that our proposed method is more efficient in determining depth estimation.Keywords
This publication has 16 references indexed in Scilit:
- T$^2$Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks2018
- Unsupervised Adversarial Depth Estimation Using Cycled Generative Networks2018
- Unsupervised Learning of Depth and Ego-Motion from Video2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Deep Residual Learning for Image Recognition2016
- High-Quality Depth from Uncalibrated Small Motion Clip2016
- Deep convolutional neural fields for depth estimation from a single image2015
- Fully convolutional networks for semantic segmentation2015
- Learning to be a depth camera for close-range human capture and interactionACM Transactions on Graphics, 2014
- Depth Transfer: Depth Extraction from Video Using Non-Parametric SamplingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014