Boundary-induced and scene-aggregated network for monocular depth prediction
作者：
Highlights：
• The problems of predicting the incorrect farthest region and the blurred depth around boundaries are deeply explored.
• The Boundary-induced and scene-aggregated network is proposed to address the two issues above.
• A well-designed DCE obtains the correlations between long-distance pixels and the correlations between multi-scale regions.
• To extract the depth boundary, a BUBF module is designed to gradually fuse features of adjacent levels.
• A Stripe Refinement Module (SRM) is designed to refine depth around the boundary.
• Numerous experiments on the NYUD v2, iBims-1, SUN-RGBD dataset prove the effectiveness of our method.
摘要
•The problems of predicting the incorrect farthest region and the blurred depth around boundaries are deeply explored.•The Boundary-induced and scene-aggregated network is proposed to address the two issues above.•A well-designed DCE obtains the correlations between long-distance pixels and the correlations between multi-scale regions.•To extract the depth boundary, a BUBF module is designed to gradually fuse features of adjacent levels.•A Stripe Refinement Module (SRM) is designed to refine depth around the boundary.•Numerous experiments on the NYUD v2, iBims-1, SUN-RGBD dataset prove the effectiveness of our method.
论文关键词：Monocular depth prediction,Boundary-induced,Depth correlation
论文评审过程：Received 19 July 2020, Revised 7 January 2021, Accepted 11 February 2021, Available online 18 February 2021, Version of Record 1 March 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.107901
