SIFT-flow-based color correction for multi-view video
作者：
Highlights：
• Propose to exploit SIFT flow to conduct color correction for multi-view video.
• Use SIFT flow to identify all common corresponding points across all the views.
• Compute the reference color by averaging the color of the common corresponding points.
• Generate color correction matrix by minimizing the energy of color difference.
• Experimental results clearly justify the effectiveness of the proposed method.
摘要
Highlights•Propose to exploit SIFT flow to conduct color correction for multi-view video.•Use SIFT flow to identify all common corresponding points across all the views.•Compute the reference color by averaging the color of the common corresponding points.•Generate color correction matrix by minimizing the energy of color difference.•Experimental results clearly justify the effectiveness of the proposed method.
论文关键词：Multi-view video,Color variation,Color correction,SIFT flow,MVC
论文评审过程：Received 31 July 2013, Revised 25 April 2015, Accepted 28 May 2015, Available online 11 June 2015, Version of Record 25 June 2015.
论文官网地址：https://doi.org/10.1016/j.image.2015.05.008
