Human visual system inspired saliency guided edge preserving tone-mapping for high dynamic range imaging
Nipu Rani Barai, Matthew J. Kyan, Dimitrios Androutsos · 2017
With the growing popularity of High Dynamic Range Imaging (HDR), the necessity for advanced tone-mapping techniques has greatly increased. We propose a Human Visual System (HVS)-inspired Saliency Guided Edge-preserving Tone Mapping method (HSGETM) that uses saliency region information of an HDR image as input to the guided filter for a base and detail image layer separation. After detail layer enhancement and base layer compression with constant weights, a new edge preserved tone mapped image is composed by adding the layers back together with saturation and exposure adjustments. The filter operation is faster due to the use of the guided filter which has O(N) time operation with N number of pixels. Experimental results demonstrate that the HSGETM has higher edge, and naturalness preserving capability, which is homologous to the HVS, as compared to other state-of-the-art tone mapping approaches.