A Residual Solver and Its Unfolding Neural Network for Total Variation Regularized Models
This paper proposes to solve the Total Variation regularized models by finding the residual between the input and the unknown optimal solution. After analyzing a previous method, we developed a new iterative algorithm, named as Residual Solver, which implicitly solves the model in gradient domain. We theoretically prove the uniqueness of the gradient field in our algorithm. We further numerically confirm that the residual solver can reach the same global optimal solutions as the classical method on 500 natural images. Moreover, we unfold our iterative algorithm into a convolution neural network (named as Residual Solver Network). This network is unsupervised and can be considered as an "enhanced version" of our iterative algorithm. Finally, both the proposed algorithm and neural network are successfully applied on several problems to demonstrate their effectiveness and efficiency, including image smoothing, denoising, and biomedical image reconstruction. The proposed network is general and can be applied to solve other total variation regularized models.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImage Reconstructionimage smoothingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning to solve TV regularized problems with unrolled algorithms
Total Variation (TV) is a popular regularization strategy that promotes piece-wise constant signals by constraining the $\ell_1$-norm of the first order derivative of the estimated signal. The resulting optimization prob…
Learning to solve TV regularised problems with unrolled algorithms
Total Variation (TV) is a popular regularization strategy that promotes piece-wise constant signals by constraining the ℓ1-norm of the first order derivative of the estimated signal. The resulting optimization problem is…
10-shot image generationSolving the L1 regularized least square problem via a box-constrained smooth minimization
In this paper, an equivalent smooth minimization for the L1 regularized least square problem is proposed. The proposed problem is a convex box-constrained smooth minimization which allows applying fast optimization metho…
General Total Variation Regularized Sparse Bayesian Learning for Robust Block-Sparse Signal Recovery
Block-sparse signal recovery without knowledge of block sizes and boundaries, such as those encountered in multi-antenna mmWave channel models, is a hard problem for compressed sensing (CS) algorithms. We propose a novel…
compressed sensingVariational Deep Unfolding with Mamba-Based Nonlocal Modeling for Underwater Image Enhancement
Underwater imaging plays a crucial role in ocean engineering, although captured data often suffer from poor visibility and color distortion. To address these challenges, we propose a model-based deep unfolding network fo…
Image Enhancement