Alexander Effland,Erich Kobler,Thomas Pock et al.
Alexander Effland et al.
This paper combines image metamorphosis with deep features. To this end, images are considered as maps into a high-dimensional feature space and a structure-sensitive, anisotropic flow regularization is incorporated in the metamorphosis mod...
Sparse reconstruction of log-conductivity in current density impedance tomography [0.03%]
电流密度阻抗断层扫描中日志电导率的稀疏重建
Madhu Gupta,Rohit Kumar Mishra,Souvik Roy
Madhu Gupta
A new non-linear optimization approach is proposed for the sparse reconstruction of log-conductivities in current density impedance imaging. This framework comprises of minimizing an objective functional involving a least squares fit of the...
Bilevel Parameter Learning for Higher-Order Total Variation Regularisation Models [0.03%]
高阶总变异regularisation模型的 bilevel 参数学习法
J C De Los Reyes,C-B Schönlieb,T Valkonen
J C De Los Reyes
We consider a bilevel optimisation approach for parameter learning in higher-order total variation image reconstruction models. Apart from the least squares cost functional, naturally used in bilevel learning, we propose and analyse an alte...
Johannes Schwab,Stephan Antholzer,Markus Haltmeier
Johannes Schwab
Deep learning and (deep) neural networks are emerging tools to address inverse problems and image reconstruction tasks. Despite outstanding performance, the mathematical analysis for solving inverse problems by neural networks is mostly mis...
S Arridge,A Hauptmann
S Arridge
A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for application...
A Convex Variational Model for Learning Convolutional Image Atoms from Incomplete Data [0.03%]
基于不完整数据学习卷积图像原子的凸变分模型
A Chambolle,M Holler,T Pock
A Chambolle
A variational model for learning convolutional image atoms from corrupted and/or incomplete data is introduced and analyzed both in function space and numerically. Building on lifting and relaxation strategies, the proposed approach is conv...
Variational Networks: An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration [0.03%]
变分网络：用于早期停止图像恢复变分方法的最优控制方法
Alexander Effland,Erich Kobler,Karl Kunisch et al.
Alexander Effland et al.
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 origina...
Tracking of Lines in Spherical Images via Sub-Riemannian Geodesics in [Formula: see text] [0.03%]
球形图像中的线跟踪via[subformula]中的子黎曼测地线
A Mashtakov,R Duits,Yu Sachkov et al.
A Mashtakov et al.
In order to detect salient lines in spherical images, we consider the problem of minimizing the functional ∫ 0 l C ( γ ( s ) ) ξ 2 + k g 2 ( s ) d s for a curve γ on a sphere with fixed boundary points and directi...
Tuomo Valkonen,Thomas Pock
Tuomo Valkonen
We propose several variants of the primal-dual method due to Chambolle and Pock. Without requiring full strong convexity of the objective functions, our methods are accelerated on subspaces with strong convexity. This yields mixed rates, O ...
Michael Roberts,Jack Spencer
Michael Roberts
Selective segmentation involves incorporating user input to partition an image into foreground and background, by discriminating between objects of a similar type. Typically, such methods involve introducing additional constraints to generi...