论文信息 - Controlled Inverse Diffusion Models for Image Restoration and Enhancement

Controlled Inverse Diffusion Models for Image Restoration and Enhancement

A new class of variational-PDE based models is proposed for edge preserving image enhancement. Using the equivalence relation between regularization and PDEs we propose a general class of models which restore noisy images with selective enhancement. It contains a controlled inverse diffusion term which sharpens the image. Experiments show the effectiveness of the model with real and MRI images.

V. B. Surya Prasath | Arindama Singh | Arindama Singh

[1] Yehoshua Y. Zeevi,et al. Forward-and-backward diffusion processes for adaptive image enhancement and denoising , 2002, IEEE Trans. Image Process..

[2] L. Álvarez,et al. Signal and image restoration using shock filters and anisotropic diffusion , 1994 .

[3] K. N Nordstrom. Biased Anisotropic Diffusion--A Unified Regularization and Diffusion , 1989 .

[4] Wenyuan Xu,et al. Behavioral analysis of anisotropic diffusion in image processing , 1996, IEEE Trans. Image Process..

[5] N. Sochen,et al. Image Sharpening by Flows Based on Triple Well Potentials , 2004 .

[6] L. Rudin,et al. Nonlinear total variation based noise removal algorithms , 1992 .

[7] Karel J. Zuiderveld,et al. Contrast Limited Adaptive Histogram Equalization , 1994, Graphics Gems.

[8] L. Rudin,et al. Feature-oriented image enhancement using shock filters , 1990 .

[9] Jitendra Malik,et al. Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10] Niklas Nordström. Biased Anisotropic Diffusion - A Unified Regularization and Diffusion Approach to Edge Detection , 1990, ECCV.