Accelerating Translational Image Registration for HDR Images on GPU

July 13, 2020 · Entered Twilight · 🏛 arXiv.org

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: Project.cu, README.md, input, kernels.h, output, stb-master

Authors Kadir Cenk Alpay, Kadir Berkay Aydemir, Alptekin Temizel arXiv ID 2007.06483 Category cs.CV: Computer Vision Cross-listed cs.DC Citations 1 Venue arXiv.org Repository https://github.com/kadircenk/WardMTBCuda ⭐ 12 Last Checked 2 months ago

Abstract

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