Human Depth Maps Restoration Based on Guided GAN

Authors

Jingfang Yin, 1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;;
Dengming Zhu, 1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;;3. Taicang-CAS Institute of Information and Technology, Taicang 215400, China;
Shi Min, 2. University of Chinese Academy of Sciences, Beijing 102206, China;;
Zhaoqi Wang, 1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;;3. Taicang-CAS Institute of Information and Technology, Taicang 215400, China;

Abstract

Abstract: The depth maps captured by a small depth camera on mobile devices suffer from the problem of severe holes. The Guided Generative Adversarial Network (Guided GAN) based on deep learning is proposed to restore human depth maps with above problems. The high-precision human segmentation features and depth class features are extracted from the monocular RGB image by the guider based on the stacked hourglass network. The holes in the human depth maps are filled by the special generator under the guidance of the extracted human features. In order to get the more realistic results, the discriminator is introduced to optimize the generator. The experimental results show that the proposed method can restore the human depth maps effectively in the existing human datasets and the dataset collected by the small depth camera. It achieves better results than the existing method.

Recommended Citation

Yin, Jingfang; Zhu, Dengming; Min, Shi; and Wang, Zhaoqi (2020) "Human Depth Maps Restoration Based on Guided GAN," Journal of System Simulation: Vol. 32: Iss. 7, Article 12.
DOI: 10.16182/j.issn1004731x.joss.19-VR0462
Available at: https://dc-china-simulation.researchcommons.org/journal/vol32/iss7/12

First Page

1312

Revised Date

2019-11-13

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.19-VR0462

Last Page

1321

CLC

TP391.9

Recommended Citation

Yin Jingfang, Zhu Dengming, Shi Min, Wang Zhaoqi. Human Depth Maps Restoration Based on Guided GAN[J]. Journal of System Simulation, 2020, 32(7): 1312-1321.

Corresponding Author

Dengming Zhu,

DOI

10.16182/j.issn1004731x.joss.19-VR0462