Detail-enhanced fusion of differently exposed images

In a typical processing chain of an image enhancement, an exposure fusion scheme can be used which usually includes smoothing effect which allows prevention of occurrence of seams in the final image. But such step usually comes with a price of losing fine details thereby blurring the final image, which then makes the scheme unable to preserve fine details as good as high dynamic range (HDR) imaging schemes. In this paper, we introduce a new quadratic optimization based method to extract fine details from a vector field. The new method extracts fine details from a set of differently exposed low dynamic range (LDR) images simultaneously. The extracted details are then added to an intermediate image that is fused by simply using an existing exposure fusion scheme. With this, the proposed scheme can preserve fine details as good as a normal HDR imaging scheme.