Abstract
Many methods have been proposed to learn image priors from natural images for the ill-posed image restoration tasks. However, many prior learning algorithms assume that a general prior distribution is suitable for over all kinds of images. Since the contents of the natural images and the corresponding low-level statistical characteristics vary from scene to scene, we argue that learning a universal generative prior for all natural images may be imperfect. Although the universal generative prior can remove artifacts and reserve a natural smoothness in image restoration, it also tends to introduce unreal flatness and clutter textures. To address this issue, in this paper, we present to learn a scene-aware image prior based on the high-order Markov random field (MRF) model (SA-MRF). With this model, we jointly learn a set of shared low-level features and different potentials for specific scene contents. In prediction, a good prior can be adapted to the given degenerated image with the scene content perception. Experimental results on the image denoising and inpainting tasks demonstrate the efficiency of the SA-MRF on both numerical evaluation and visual compression.
Highlights
Image restoration tasks, such as denoising (Tappen et al 2007; Schmidt et al 2010; Schmidt and Roth 2014), deblurring (Krishnan and Fergus 2009; Krishnan et al 2011; Levin et al 2009; Zhang et al 2013; Gong et al 2016, 2017) and super resolution (Tappen and Liu 2012) are all inherently ill-posed
We propose a scene-aware Markov random field (SAMRF) model to capture the scene-discriminating statistical prior of any whole natural image; the SA-MRF model owes high-order non-Gaussian potential conditioned on a scene coefficient extracted from high-level concepts of observations
Evaluation on image denoising We focus on comparing our denoising results to the reconstructs relying on the state-ofthe-art generative MRF prior in Schmidt et al (2010) and another broadly used denoising technique BM3D (Dabov et al 2007), using peak signal-to-noise ratio (PSNR) and gray-scale structural similarity (SSIM) (Wang et al 2004)
Summary
Image restoration tasks, such as denoising (Tappen et al 2007; Schmidt et al 2010; Schmidt and Roth 2014), deblurring (Krishnan and Fergus 2009; Krishnan et al 2011; Levin et al 2009; Zhang et al 2013; Gong et al 2016, 2017) and super resolution (Tappen and Liu 2012) are all inherently ill-posed. Some knowledge of natural images is used as prior to boost the estimation stability and to recover information lost in non-ideal imaging processes. Many image priors work on image gradients for briefness of modeling and better performance (Fergus et al 2006; Levin et al 2007, 2009; Krishnan et al 2011; Krishnan and Fergus 2009; Xu et al 2013; Zhang et al 2013). The representation of image prior distribution in gradient domain is fragile for sophisticated concept of natural, as the variant of image content and/or scale makes the gradient characteristics unstable for modeling the unique clear individual images. Motivated by the demand of capturing stable and accurate prior knowledge of natural image, many low-level modeling technologies including feature representation and related distribution are studied. Recent years have seen a trend to figure out this issue through the use of probabilistic graphical models (e.g., MRF and CRF) with
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.