TY - GEN
T1 - A map estimation framework for HDR video synthesis
AU - Li, Yuelong
AU - Lee, Chul
AU - Monga, Vishal
PY - 2015/12/9
Y1 - 2015/12/9
N2 - High dynamic range (HDR) image synthesis from multiple low dynamic range (LDR) exposures continues to be a topic of great interest. The extension to HDR video comprises a stiff challenge due to significant motion. In particular, loss of data due to poor exposures introduces great difficulty in exact motion estimation, and under such circumstances conventional optical flow calculation techniques usually fail. We propose a maximum a posterior (MAP) estimation framework for HDR video synthesis algorithm free of explicit optical flow calculation. We formulate HDR video synthesis as a MAP estimation problem, which subsequently can be reduced to an optimization problem based on meaningful statistical assumptions on foreground and background regions of the input video. In the background regions the underlying scenes are static, while in the foreground regions motion information is captured implicitly by a modified 3D steering kernel regression (3D SKR) approach. Solution to the optimization problem provides us with temporally coherent HDR video sequences without noticeable artifacts. Experimental results on challenging LDR video sets demonstrate that our proposed algorithm can achieve HDR video quality that is competitive with or better than state of the art alternatives.
AB - High dynamic range (HDR) image synthesis from multiple low dynamic range (LDR) exposures continues to be a topic of great interest. The extension to HDR video comprises a stiff challenge due to significant motion. In particular, loss of data due to poor exposures introduces great difficulty in exact motion estimation, and under such circumstances conventional optical flow calculation techniques usually fail. We propose a maximum a posterior (MAP) estimation framework for HDR video synthesis algorithm free of explicit optical flow calculation. We formulate HDR video synthesis as a MAP estimation problem, which subsequently can be reduced to an optimization problem based on meaningful statistical assumptions on foreground and background regions of the input video. In the background regions the underlying scenes are static, while in the foreground regions motion information is captured implicitly by a modified 3D steering kernel regression (3D SKR) approach. Solution to the optimization problem provides us with temporally coherent HDR video sequences without noticeable artifacts. Experimental results on challenging LDR video sets demonstrate that our proposed algorithm can achieve HDR video quality that is competitive with or better than state of the art alternatives.
UR - http://www.scopus.com/inward/record.url?scp=84956708609&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84956708609&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2015.7351195
DO - 10.1109/ICIP.2015.7351195
M3 - Conference contribution
AN - SCOPUS:84956708609
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2219
EP - 2223
BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PB - IEEE Computer Society
T2 - IEEE International Conference on Image Processing, ICIP 2015
Y2 - 27 September 2015 through 30 September 2015
ER -