On robust optical flow estimation on image sequences with differently exposed frames using primal–dual optimization

作者：

Highlights：

• A novel method for optical flow estimation for high dynamic range scenes is proposed.

• The mathematical model can utilize images taken with arbitrary exposure settings.

• Flow estimation of points in saturated image regions is successfully achieved.

摘要

•A novel method for optical flow estimation for high dynamic range scenes is proposed.•The mathematical model can utilize images taken with arbitrary exposure settings.•Flow estimation of points in saturated image regions is successfully achieved.

论文关键词：Optical flow estimation,High dynamic range,Temporal coherency,Primal–dual

论文评审过程：Received 15 February 2016, Revised 10 September 2016, Accepted 5 November 2016, Available online 15 November 2016, Version of Record 4 December 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.11.003