High-dynamic-range parallel multi-scale retinex enhancement with spatially-adaptive prior

摘要

We propose a parallel multi-scale retinex enhancement to synthesize a high-dynamic-range(HDR, HDR-like) image from a single low-dynamic-range (LDR) input. Since an image is composed of illumination and reflectance, we can enhance these two components to obtain our HDR results. First, we estimate the illumination from the input by optimizing a cost function with a spatially-adaptive edge prior. Then, we tune up the estimated illumination while enhance the reflection so as to synthesize the HDR result. In addition, we adopt parallel multi-scale acceleration for speed-up. Experimental results demonstrate that our retinex approach is promising as compared to the existing methods.