A Novel Approach for Computing Quality Map of Visual Information Fidelity Index

The visual information fidelity (VIF) index gained widespread popularity as a tool to assess the quality of images and to evaluate the performance of image processing algorithms and systems. But VIF is not a map-based quality metric if its quality map is calculated by traditional sliding window approach. This map-based property is owned by the other quality metrics such as structural similarity (SSIM) and mean-squared error (MSE). In this article, we first construct a novel VIF quality map in pixel domain, which makes VIF become a Minkowski norm of its quality map. Furthermore, we deduce the gradient of VIF by taking the derivative of VIF index with respect to the reference image. The gradient of VIF is easy to calculate and has many useful applications. Experimental results show that the proposed quality map can provide useful guidance on how local image quality is similar to reference image.