Accelerating Translational Image Registration for HDR Images on GPU
This work provides a faster method for HDR image alignment, which is incremental as it accelerates an existing technique.
The paper tackles the problem of aligning multiple exposure images for HDR generation by optimizing translational image registration using GPU parallel processing, achieving a speed-up of up to 6.24 times over a multi-threaded CPU baseline.
High Dynamic Range (HDR) images are generated using multiple exposures of a scene. When a hand-held camera is used to capture a static scene, these images need to be aligned by globally shifting each image in both dimensions. For a fast and robust alignment, the shift amount is commonly calculated using Median Threshold Bitmaps (MTB) and creating an image pyramid. In this study, we optimize these computations using a parallel processing approach utilizing GPU. Experimental evaluation shows that the proposed implementation achieves a speed-up of up to 6.24 times over the baseline multi-threaded CPU implementation on the alignment of one image pair. The source code is available at https://github.com/kadircenk/WardMTBCuda