Deep High Dynamic Range Imaging without Motion Artifacts Using Global and Local Skip Connections

Abstract

This paper proposes a new HDR image generation method using a deep residual network. The proposed method aligns input images of three low dynamic range (LDR) images with different exposure times for the same scene based on the images with intermediate exposure times and uses them as input to the network. In the network, three LDR images and three images converted into high dynamic range (HDR) regions are input, and three LDR images with improved artifacts and an alpha map are output to generate HDR images. The method proposed through the experimental results can show HDR images without color distortion or ghosting artifact when compared to the existing method, and good performance compared to the HDR function used in consumer imaging systems.