Saliency Guided Image Detail Enhancement

The use of visual saliency for perceptual enhancement of images has drawn significant attention. In this paper, we explore the idea of selectively enhancing salient regions of an image. Moreover, we develop an algorithm based on adaptive bilateral filtering for this purpose. In most of the filtering based methods, detail enhancement is performed by decomposing the image into base and detail layers; the detail layer is amplified and added back to the base layer to obtain the enhanced image. The decomposition is performed using edge-preserving smoothing such as bilateral filtering. The present novelty is that we use the saliency map to locally guide the smoothing (and the enhancement) action of the bilateral filter. The effectiveness of our proposal is demonstrated using visual results. In particular, our method does not suffer from gradient reversals and halo artifacts, and does not amplify fine details in non-salient regions that often appear as noise grains in the enhanced image. Moreover, if we choose to perform the filtering channelwise, then our method can be efficiently implemented using an existing fast algorithm.