Depth Estimation from Monocular Image and Coarse Depth Points based on Conditional GAN

摘要：

　　Depth estimation has achieved considerable success with the development of the depth sensor devices and deep learning method.However,depth estimation from monocular RGB-based image will increase ambiguity and is prone to error.In this paper,we present a novel approach to produce dense depth map from a single image coupled with coarse point-cloud samples.Our approach learns to fit the distribution of the depth map from source data using conditional adversarial networks and convert the sparse point clouds to dense maps.Our experiments show that the use of the conditional adversarial networks can add full image information to the predicted depth maps and the effectiveness of our approach to predict depth in NYU-Depth-v2 indoor dataset.

作者: Yaoxin Li Keyuan Qian Tao Huang Jingkun Zhou

作者单位: Department of Electronic Engineering,Tsinghua University,Beijing 100084,China Graduate School at Shenzhen,Tsinghua University,Shenzhen 518055,China

会议类型: 国际会议

会议名称: 2018年建筑、航空与环境工程国际学术论坛-物联网(IFCAE-IOT 2018)2018 International Forum on Construction, Aviation and Environmental Engineering-Internet of Things(IFCAE-IOT 2018)

会议地点: 广州

会议语种:英文

页码: 1-5

在线出版日期: 2018-05-11（万方平台首次上网日期，不代表论文的发表时间）