Improving Image Enhancement by Gradient Fusion

We present a fusion approach in the gradient domain to combine complementary advantages between image enhancement results for visualization improvement. A weighted structure tensor is employed to capture significant details of each input channel, and local contrast is incorporated in the design of fusion weights. Experimental results demonstrate that the fused image can preserve significant detail and structural information of each input image, and the visual effect is improved.

[1]  Jan Kautz,et al.  Exposure Fusion , 2009, 15th Pacific Conference on Computer Graphics and Applications (PG'07).

[2]  Michael Elad,et al.  A Variational Framework for Retinex , 2002, IS&T/SPIE Electronic Imaging.

[3]  Gemma Piella,et al.  Image Fusion for Enhanced Visualization: A Variational Approach , 2009, International Journal of Computer Vision.

[4]  Joachim Weickert,et al.  Anisotropic diffusion in image processing , 1996 .

[5]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[6]  Yücel Altunbasak,et al.  A Histogram Modification Framework and Its Application for Image Contrast Enhancement , 2009, IEEE Transactions on Image Processing.

[7]  Zia-ur Rahman,et al.  A multiscale retinex for bridging the gap between color images and the human observation of scenes , 1997, IEEE Trans. Image Process..

[8]  Laurence Meylan,et al.  High dynamic range image rendering with a retinex-based adaptive filter , 2006, IEEE Transactions on Image Processing.

[9]  Xin Xu,et al.  A solution to the deficiencies of image enhancement , 2010, Signal Process..

[10]  Sandy Irani,et al.  Perception-based contrast enhancement of images , 2007, TAP.

[11]  Dani Lischinski,et al.  Gradient Domain High Dynamic Range Compression , 2023 .