A Color Elastica Model for Vector-Valued Image Regularization

• URL: http://arxiv.org/abs/2008.08255v2
• Date: Thu, 4 Mar 2021 00:42:25 GMT
• Title: A Color Elastica Model for Vector-Valued Image Regularization
• Authors: Hao Liu, Xue-Cheng Tai, Ron Kimmel, Roland Glowinski
• Abstract summary: We introduce an addition to the Polyakov action for color images that minimizes the color manifold curvature. Finding a minimizer for the proposed nonlinear geometric model is a challenge we address in this paper.
• Score: 14.430905433555248
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Models related to the Euler's elastica energy have proven to be useful for many applications including image processing. Extending elastica models to color images and multi-channel data is a challenging task, as stable and consistent numerical solvers for these geometric models often involve high order derivatives. Like the single channel Euler's elastica model and the total variation (TV) models, geometric measures that involve high order derivatives could help when considering image formation models that minimize elastic properties. In the past, the Polyakov action from high energy physics has been successfully applied to color image processing. Here, we introduce an addition to the Polyakov action for color images that minimizes the color manifold curvature. The color image curvature is computed by applying of the Laplace-Beltrami operator to the color image channels. When reduced to gray-scale images, while selecting appropriate scaling between space and color, the proposed model minimizes the Euler's elastica operating on the image level sets. Finding a minimizer for the proposed nonlinear geometric model is a challenge we address in this paper. Specifically, we present an operator-splitting method to minimize the proposed functional. The non-linearity is decoupled by introducing three vector-valued and matrix-valued variables. The problem is then converted into solving for the steady state of an associated initial-value problem. The initial-value problem is time-split into three fractional steps, such that each sub-problem has a closed form solution, or can be solved by fast algorithms. The efficiency and robustness of the proposed method are demonstrated by systematic numerical experiments.

Related papers

• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• Super-Resolution Surface Reconstruction from Few Low-Resolution Slices [7.053276723038573]
  This paper proposes a new variational model for increasing the resolution of segmented surfaces in numerical simulations. We implement two numerical algorithms for solving the model, a projected gradient descent method and the alternating direction method of multipliers. The advantages of the new model are shown through quantitative comparisons by the standard deviation of Gaussian curvatures and mean curvatures from the viewpoint of discrete geometry.
  arXiv  Detail & Related papers  (2023-09-10T16:32:02Z)
• An Optimization-based Deep Equilibrium Model for Hyperspectral Image Deconvolution with Convergence Guarantees [71.57324258813675]
  We propose a novel methodology for addressing the hyperspectral image deconvolution problem. A new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network. The derived iterative solver is then expressed as a fixed-point calculation problem within the Deep Equilibrium framework.
  arXiv  Detail & Related papers  (2023-06-10T08:25:16Z)
• Multi-channel Nuclear Norm Minus Frobenius Norm Minimization for Color Image Denoising [9.20787253404652]
  One traditional strategy is to convert the RGB image to a less correlated color space and denoise each channel of the new space separately. This paper proposes a new multi-channel optimization model for color image denoising under the nuclear norm minus Frobenius norm minimization framework. Experimental results on both synthetic and real noise datasets demonstrate the proposed model outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2022-09-16T04:10:29Z)
• A variational neural network approach for glacier modelling with nonlinear rheology [1.4438155481047366]
  We first formulate the solution of non-Newtonian ice flow model into the minimizer of a variational integral with boundary constraints. The solution is then approximated by a deep neural network whose loss function is the variational integral plus soft constraint from the mixed boundary conditions. To address instability in real-world scaling, we re-normalize the input of the network at the first layer and balance the regularizing factors for each individual boundary.
  arXiv  Detail & Related papers  (2022-09-05T18:23:59Z)
• Elastica Models for Color Image Regularization [14.430905433555248]
  Minimizing the area of the image manifold leads to the Beltrami flow or mean curvature flow of the image surface in the 3D color space. We introduce two new models for color image regularization.
  arXiv  Detail & Related papers  (2022-03-18T14:47:33Z)
• Message Passing Neural PDE Solvers [60.77761603258397]
  We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators. We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes. We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
  arXiv  Detail & Related papers  (2022-02-07T17:47:46Z)
• Model reduction for the material point method via learning the deformation map and its spatial-temporal gradients [9.509644638212773]
  The technique approximates the $textitkinematics$ by approximating the deformation map in a manner that restricts deformation trajectories to reside on a low-dimensional manifold. The ability to generate material points also allows for adaptive quadrature rules for stress update.
  arXiv  Detail & Related papers  (2021-09-25T15:45:14Z)
• Cogradient Descent for Dependable Learning [64.02052988844301]
  We propose a dependable learning based on Cogradient Descent (CoGD) algorithm to address the bilinear optimization problem. CoGD is introduced to solve bilinear problems when one variable is with sparsity constraint. It can also be used to decompose the association of features and weights, which further generalizes our method to better train convolutional neural networks (CNNs)
  arXiv  Detail & Related papers  (2021-06-20T04:28:20Z)
• Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
  Blind image restoration is a common yet challenging problem in computer vision. We propose a novel blind image restoration method, aiming to integrate both the advantages of them. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
  arXiv  Detail & Related papers  (2020-08-25T03:30:53Z)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.