Multi-exposure image fusion of dynamic scenes using consistency detection and weighted least squares filtering

Abstract

The high dynamic range image obtained by multi-exposure image fusion (MEF) contains more detailed information, which has broad application prospects and crucial practical significance in many fields. However, due to the introduction of the ghosting artifacts caused by object movement and camera shake, MEF in the dynamic scenes has always been a challenge. To address this problem, we designed a deghosting method for MEF. The over- and under-exposed images are corrected by intensity mapping and consistency detection to obtain the aligned latent images. Then the high- and low-frequency components of the latent images are generated using weighted least squares filtering. The blending weights are calculated based on the image luminance and the exposedness function. These frequency components are integrated into the final deghosted image with more texture details and vivid color. A comprehensive evaluation experiment is carried out, proving that the proposed method has a better visual effect and stable performance than the state-of-the-art deghosting MEF methods.