Depth map upsampling with a confidence-based joint guided filter
作者：
Highlights：
• It proposes the confidence-based upsampling scheme for depth map.
• The confidence values are computed from the shape of edge and color-depth correlation.
• Then, the confidence values adjust the filter parameters for the guided filter instead of the geometric proximity.
• The guided filtering is iteratively applied to refine the unreliable regions.
• The proposed method greatly improves the qualitative and quantitative performance.
摘要
•It proposes the confidence-based upsampling scheme for depth map.•The confidence values are computed from the shape of edge and color-depth correlation.•Then, the confidence values adjust the filter parameters for the guided filter instead of the geometric proximity.•The guided filtering is iteratively applied to refine the unreliable regions.•The proposed method greatly improves the qualitative and quantitative performance.
论文关键词：Upsampling,Super-resolution,Depth map,Confidence map,Guided filter
论文评审过程：Received 8 September 2018, Revised 9 January 2019, Accepted 28 May 2019, Available online 30 May 2019, Version of Record 4 June 2019.
论文官网地址：https://doi.org/10.1016/j.image.2019.05.014
