DPNet: Detail-preserving network for high quality monocular depth estimation

作者：

Highlights：

• A dual-branch depth estimation network architecture that separately captures low-level and high-level feature representations.

• A refinement module is proposed to fuse different levels of features from both the branches and obtain the final high-quality depth map.

• A nonlocal spatial attention module is proposed to explicitly exploit the nonlocal correlation in spatial domain.

摘要

•A dual-branch depth estimation network architecture that separately captures low-level and high-level feature representations.•A refinement module is proposed to fuse different levels of features from both the branches and obtain the final high-quality depth map.•A nonlocal spatial attention module is proposed to explicitly exploit the nonlocal correlation in spatial domain.

论文关键词：Depth estimation,Detail-preserving,Spatial,Attention,Depth map

论文评审过程：Received 31 August 2019, Revised 15 June 2020, Accepted 4 August 2020, Available online 25 August 2020, Version of Record 28 August 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107578