Paper Info
Title
Speeding up tone mapping operators: Exploiting parallelism for real-time, high dynamic range video
Abstract
Tone mapping operators map high dynamic range images so that they can be displayed with a high dynamic range appearance in a limited range medium. However, due to their large computational complexity, sequential implementation of these operators on CPU cannot achieve the frame rate needed for real-time video image processing. In this paper, we revisit these operators to simplify them so that we can speed up their execution and to exploit their parallelism on compute, graphical processing unit (compute-GPU). We offer implementations of these operators that achieve significant speedups. For example, for a 1080×1920 pixels image, our simplified Reinhard's global tone mapping implementation executes on a compute-GPU in 0.429 milliseconds, which is nearly a speedup factor of 700 over CPU sequential implementation in OpenCV. We also offer implementations of local tone mapping operators that take advantage of shared memory on compute-GPU to minimize operators' execution time.
Year
DOI
Venue
2017
10.1109/MWSCAS.2017.8052893
2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS)
Keywords
Field
DocType
high dynamic range video,real-time,graphics processing units
Central processing unit,Shared memory,Computer science,Parallel computing,Image processing,Tone mapping,Operator (computer programming),Frame rate,High dynamic range,Speedup
Conference
ISBN
Citations 
PageRank 
978-1-5090-6390-1
0
0.34
References 
Authors
6
2
Name
Order
Citations
PageRank
Ziad Youssfi100.68
Hassan, F.264.59