Next Article in Journal
Reducing False Arrhythmia Alarms Using Different Methods of Probability and Class Assignment in Random Forest Learning Methods
Next Article in Special Issue
Single-Image Depth Inference Using Generative Adversarial Networks
Previous Article in Journal
A New Maritime Moving Target Detection and Tracking Method for Airborne Forward-looking Scanning Radar
Previous Article in Special Issue
Combining Weighted Contour Templates with HOGs for Human Detection Using Biased Boosting
Open AccessArticle

Depth Map Upsampling via Multi-Modal Generative Adversarial Network

1
Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei 10607, Taiwan
2
Center for Automation Research, College of Computer Studies, De La Salle University, Manila 1004, Philippines
3
Center for Cyber-Physical System Innovation, National Taiwan University of Science and Technology, Taipei 10607, Taiwan
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(7), 1587; https://doi.org/10.3390/s19071587
Received: 16 February 2019 / Revised: 28 March 2019 / Accepted: 29 March 2019 / Published: 2 April 2019
(This article belongs to the Special Issue Selected Papers from INNOV 2018)
Autonomous robots for smart homes and smart cities mostly require depth perception in order to interact with their environments. However, depth maps are usually captured in a lower resolution as compared to RGB color images due to the inherent limitations of the sensors. Naively increasing its resolution often leads to loss of sharpness and incorrect estimates, especially in the regions with depth discontinuities or depth boundaries. In this paper, we propose a novel Generative Adversarial Network (GAN)-based framework for depth map super-resolution that is able to preserve the smooth areas, as well as the sharp edges at the boundaries of the depth map. Our proposed model is trained on two different modalities, namely color images and depth maps. However, at test time, our model only requires the depth map in order to produce a higher resolution version. We evaluated our model both quantitatively and qualitatively, and our experiments show that our method performs better than existing state-of-the-art models. View Full-Text
Keywords: depth upsampling; encoder-decoder networks; generative adversarial networks depth upsampling; encoder-decoder networks; generative adversarial networks
Show Figures

Figure 1

MDPI and ACS Style

Tan, D.S.; Lin, J.-M.; Lai, Y.-C.; Ilao, J.; Hua, K.-L. Depth Map Upsampling via Multi-Modal Generative Adversarial Network. Sensors 2019, 19, 1587.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop