Variational method for joint optical flow estimation and edge-aware image restoration

详细信息    查看全文

• 作者：Zhigang Tu^a ; ^{Zhigang.Tu@asu.edu}Author Vitae ; Wei Xie^b ; ^{XW@mail.ccnu.edu.cn}Author Vitae ; Jun Cao^c ; ^{Jun.Cao@intel.com}Author Vitae ; Coert van Gemeren^a ; ^{C.J.Vangemeren@uu.nl}Author Vitae ; Ronald Poppe^a ; ^{R.W.Poppe@uu.nl}Author Vitae ; Remco C. Veltkamp^a ; ^{R.C.Veltkamp@uu.nl}Author Vitae
• 关键词：Optical flow ; Image sequence restoration ; Edge preserving ; Efficient numerical solver
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：May 2017
• 年：2017
• 卷：65
• 期：Complete
• 页码：11-25
• 全文大小：1586 K
• 卷排序：65

文摘

Incorporating an EAC added IFT to the variational model to form a new energy function, which can estimate optical flow and restore images jointly. The EAC can be rewritten into the first-order gradient form, and is beneficial for preserving edges and minimization. Input images can be fast restored by optimizing the Euler–Lagrange equations of the EAC integrated IFT.