Unsupervised learning of depth estimation based on attention model and global pose optimization
作者：
Highlights：
• An attention model is adopted to preserve the details of the depth map.
• The pose is globally optimized by bundle adjustment, loop closure and relocalization.
• Experiments are conducted with results which outperform most of the current methods.
摘要
•An attention model is adopted to preserve the details of the depth map.•The pose is globally optimized by bundle adjustment, loop closure and relocalization.•Experiments are conducted with results which outperform most of the current methods.
论文关键词：Depth estimation,Attention model,Global pose optimization
论文评审过程：Received 8 February 2019, Revised 15 June 2019, Accepted 15 July 2019, Available online 16 July 2019, Version of Record 29 July 2019.
论文官网地址：https://doi.org/10.1016/j.image.2019.07.007
