Non-Convex Weighted Lp Nuclear Norm based ADMM Framework for Image Restoration
원문 초록
Since the matrix formed by nonlocal similar patches in a natural image is of low rank, the nuclear norm minimization (NNM) has been widely used in various image processing studies. Nonetheless, nuclear norm based convex surrogate of the rank function usually over-shrinks the rank components and makes different components equally, and thus may produce a result far from the optimum. To alleviate the above-mentioned limitations of the nuclear norm, in this paper we propose a new method for image restoration via the non-convex weighted Lp nuclear norm minimization (NCW-NNM), which is able to more accurately enforce the image structural sparsity and self-similarity simultaneously. To make the proposed model tractable and robust, the alternative direction multiplier method (ADMM) is adopted to solve the associated non-convex minimization problem. Experimental results on various types of image restoration problems, including image deblurring, image inpainting and image compressive sensing (CS) recovery, demonstrate that the proposed method outperforms many current state-of-the-art methods in both the objective and the perceptual qualities.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Revitalizing Convolutional Network for Image Restoration
Single Stage Adaptive Multi-Attention Network for Image Restoration
Image Restoration via Frequency Selection
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
토론
이 논문과 연결된 포럼 글이 아직 없습니다.