Depth upsampling based on deep edge-aware learning
作者：
Highlights：
• An edge inference scheme is proposed based on the designed deep edgeaware network. Note that, edge information uses the most concise representations to express the major depth information. Learning edges is less sensitive to scene characteristics, providing better cues for depth recovery.
• A fast depth filling strategy (DSR F) is proposed, which inherits the advantages of low complexity and high accuracy from local and global methods respectively, and therefore achieves far better performance than traditional local or global methods.
• A cascaded edge inference and depth restoration network (DSR N) is proposed. The proposed stacked design benefits from jointly predicting the edge map and HR depth map, which can share mutual improvements through simply aggregating supervision from each individual task.
摘要
•An edge inference scheme is proposed based on the designed deep edgeaware network. Note that, edge information uses the most concise representations to express the major depth information. Learning edges is less sensitive to scene characteristics, providing better cues for depth recovery.•A fast depth filling strategy (DSR F) is proposed, which inherits the advantages of low complexity and high accuracy from local and global methods respectively, and therefore achieves far better performance than traditional local or global methods.•A cascaded edge inference and depth restoration network (DSR N) is proposed. The proposed stacked design benefits from jointly predicting the edge map and HR depth map, which can share mutual improvements through simply aggregating supervision from each individual task.
论文关键词：Upsampling,CNN,Edge-aware,Depth map
论文评审过程：Received 26 February 2019, Revised 27 December 2019, Accepted 11 February 2020, Available online 12 February 2020, Version of Record 25 February 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107274
