Simultaneous color-depth super-resolution with conditional generative adversarial networks
作者：
Highlights：
• In consideration of the geometric structural similarity of color-depth images, a generative network is proposed to leverage mutual information of the color image and depth image to enhance each other.
• Three loss functions, including data loss, total variation loss, and 8-connected gradient difference loss are introduced to train this generative network to make generated images close to the real ones.
• We use our framework to resolve the problems of simultaneous image smoothing and edge detection, as well as HR-color-image-guided depth super-resolution to show the effectiveness and universality of the proposed method.
摘要
•In consideration of the geometric structural similarity of color-depth images, a generative network is proposed to leverage mutual information of the color image and depth image to enhance each other.•Three loss functions, including data loss, total variation loss, and 8-connected gradient difference loss are introduced to train this generative network to make generated images close to the real ones.•We use our framework to resolve the problems of simultaneous image smoothing and edge detection, as well as HR-color-image-guided depth super-resolution to show the effectiveness and universality of the proposed method.
论文关键词：Generative adversarial networks,Super-resolution,Image smoothing,Edge detection
论文评审过程：Received 25 November 2017, Revised 22 November 2018, Accepted 27 November 2018, Available online 28 November 2018, Version of Record 3 December 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.11.028
