An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration
원문 초록
We investigate a well-known phenomenon of variational approaches in image processing, where typically the best image quality is achieved when the gradient flow process is stopped before converging to a stationary point. This paradox originates from a tradeoff between optimization and modelling errors of the underlying variational model and holds true even if deep learning methods are used to learn highly expressive regularizers from data. In this paper, we take advantage of this paradox and introduce an optimal stopping time into the gradient flow process, which in turn is learned from data by means of an optimal control approach. As a result, we obtain highly efficient numerical schemes that achieve competitive results for image denoising and image deblurring. A nonlinear spectral analysis of the gradient of the learned regularizer gives enlightening insights about the different regularization properties.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Single Stage Adaptive Multi-Attention Network for Image Restoration
Image Restoration via Frequency Selection
Revitalizing Convolutional Network for Image Restoration
Deep Sparse and Low-Rank Prior for Hyperspectral Image Denoising
SAR Image Despeckling Using Continuous Attention Module
Color Image Restoration Exploiting Inter-channel Correlation with a 3-stage CNN
토론
이 논문과 연결된 포럼 글이 아직 없습니다.