arXiv Analytics

Sign in

arXiv:1708.09105 [cs.CV]AbstractReferencesReviewsResources

Simultaneously Color-Depth Super-Resolution with Conditional Generative Adversarial Network

Lijun Zhao, Jie Liang, Huihui Bai, Anhong Wang, Yao Zhao

Published 2017-08-30Version 1

Recently, Generative Adversarial Network (GAN) has been found wide applications in style transfer, image-to-image translation and image super-resolution. In this paper, a color-depth conditional GAN is proposed to concurrently resolve the problems of depth super-resolution and color super-resolution in 3D videos. Firstly, given the low-resolution depth image and low-resolution color image, a generative network is proposed to leverage mutual information of color image and depth image to enhance each other in consideration of the geometry structural dependency of color-depth image in the same scene. Secondly, three loss functions, including data loss, total variation loss, and 8-connected gradient difference loss are introduced to train this generative network in order to keep generated images close to the real ones, in addition to the adversarial loss. Experimental results demonstrate that the proposed approach produces high-quality color image and depth image from low-quality image pair, and it is superior to several other leading methods. Besides, the applications of the proposed method in other tasks are image smoothing and edge detection at the same time.

Related articles: Most relevant | Search more
arXiv:2212.13589 [cs.CV] (Published 2022-12-27)
Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification
arXiv:1701.05957 [cs.CV] (Published 2017-01-21)
Image De-raining Using a Conditional Generative Adversarial Network
arXiv:2105.09936 [cs.CV] (Published 2021-05-20)
BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image