Bidirectional Motion Estimation with Cyclic Cost Volume for High Dynamic Range Imaging

Abstract

We propose a high dynamic range (HDR) imaging algorithm based on bidirectional motion estimation. First, we develop a motion estimation network with the cyclic cost volume and spatial attention maps to estimate accurate optical flows between input low dynamic range (LDR) images. Then, we develop the dynamic local fusion network that combines the warped and reference inputs to generate a synthesized image by exploiting local information. Finally, to further improve the synthesis performance, we develop the global refinement network that generates a residual image by exploiting global information. Experimental results on the dataset from the NTIRE 2022 HDR Challenge Track 1 (Low-complexity constrain) demonstrate the effectiveness of the proposed HDR image synthesis algorithm.