this book constitutes the refereed proceedings of the 6thinternationalconference on scalespace and Variational methods in computervision, SSVM 2017, held in Kolding, Denmark, in June 2017. the 55 revised full...
详细信息
ISBN:
(数字)9783319587714
ISBN:
(纸本)9783319587707
this book constitutes the refereed proceedings of the 6thinternationalconference on scalespace and Variational methods in computervision, SSVM 2017, held in Kolding, Denmark, in June 2017. the 55 revised full papers presented were carefully reviewed and selected from 77 submissions. the papers are organized in the following topical sections: scalespace and pdemethods; Restoration and Reconstruction; Tomographic Reconstruction; Segmentation; Convex and Non-Convex Modeling and Optimization in Imaging; Optical Flow, Motion Estimation and Registration; 3D vision.
A deep learning approach to numerically approximate the solution to the Eikonal equation is introduced. the proposed method is built on the fast marching scheme which comprises of two components: a local numerical sol...
详细信息
ISBN:
(纸本)9783030223687;9783030223670
A deep learning approach to numerically approximate the solution to the Eikonal equation is introduced. the proposed method is built on the fast marching scheme which comprises of two components: a local numerical solver and an update scheme. We replace the formulaic local numerical solver with a trained neural network to provide highly accurate estimates of local distances for a variety of different geometries and sampling conditions. Our learning approach generalizes not only to flat Euclidean domains but also to curved surfaces enabled by the incorporation of certain invariant features in the neural network architecture. We show a considerable gain in performance, validated by smaller errors and higher orders of accuracy for the numerical solutions of the Eikonal equation computed on different surfaces. the proposed approach leverages the approximation power of neural networks to enhance the performance of numerical algorithms, thereby, connecting the somewhat disparate themes of numerical geometry and learning.
Variational methods are among the most accurate techniques for estimating the optic flow. they yield dense flow fields and can be designed such that they preserve discontinuities, estimate large displacements correctl...
详细信息
Variational methods are among the most accurate techniques for estimating the optic flow. they yield dense flow fields and can be designed such that they preserve discontinuities, estimate large displacements correctly and perform well under noise and varying illumination. However, such adaptations render the minimisation of the underlying energy functional very expensive in terms of computational costs: Typically one or more large linear or nonlinear equation systems have to be solved in order to obtain the desired solution. Consequently, variational methods are considered to be too slow for real-time performance. In our paper we address this problem in two ways: (i) We present a numerical framework based on bidirectional multigrid methods for accelerating a broad class of variational optic flow methods with different constancy and smoothness assumptions. thereby, our work focuses particularly on regularisation strategies that preserve discontinuities. (ii) We show by the examples of five classical and two recent variational techniques that real-time performance is possible in all cases-even for very complex optic flow models that offer high accuracy. Experiments show that frame rates up to 63 dense flow fields per second for image sequences of size 160 x 120 can be achieved on a standard PC. Compared to classical iterative methodsthis constitutes a speedup of two to four orders of magnitude.
We present pde-based Group Convolutional Neural Networks (pde-G-CNNs) that generalize Group equivariant Convolutional Neural Networks (G-CNNs). In pde-G-CNNs a network layer is a set of pde-solvers where geometrically...
详细信息
this book constitutes the refereed proceedings of the 5thinternationalconference on scalespace and Variational methods in computervision, SSVM 2015, held in Lège-Cap Ferret, France, in May 2015. the 56 revise...
详细信息
ISBN:
(数字)9783319184616
ISBN:
(纸本)9783319184609
this book constitutes the refereed proceedings of the 5thinternationalconference on scalespace and Variational methods in computervision, SSVM 2015, held in Lège-Cap Ferret, France, in May 2015. the 56 revised full papers presented were carefully reviewed and selected from 83 submissions. the papers are organized in the following topical sections: scalespace and partial differential equation methods; denoising, restoration and reconstruction, segmentation and partitioning; flow, motion and registration; photography, texture and color processing; shape, surface and 3D problems; and optimization theory and methods in imaging.
Lossy image compression methods based on partial differential equations have received much attention in recent years. they may yield high quality results but rely on the computationally expensive task of finding optim...
详细信息
ISBN:
(纸本)9783030223687;9783030223670
Lossy image compression methods based on partial differential equations have received much attention in recent years. they may yield high quality results but rely on the computationally expensive task of finding optimal data. For the possible extension to video compression, the data selection is a crucial issue. In this context one could either analyse the video sequence as a whole or perform a frame-by-frame optimisation strategy. Both approaches are prohibitive in terms of memory and run time. In this work we propose to restrict the expensive computation of optimal data to a single frame and to approximate the optimal reconstruction data for the remaining frames by prolongating it by means of an optic flow field. We achieve a notable decrease in the computational complexity. As a proof-of-concept, we evaluate the proposed approach for multiple sequences with different characteristics. We show that the method preserves a reasonable quality in the reconstruction, and is very robust against errors in the flow field.
Intelligent monitoring and fault warning of power systems are crucial for ensuring the reliability and stability of power systems. As the scale of power systems expands, power demand increases, and new energy sources ...
详细信息
Based on a new, general formulation of the geometric method of moving frames, invariantization of numerical schemes has been established during the last years as a powerful tool to guarantee symmetries for numerical s...
详细信息
ISBN:
(纸本)9783540728221
Based on a new, general formulation of the geometric method of moving frames, invariantization of numerical schemes has been established during the last years as a powerful tool to guarantee symmetries for numerical solutions while simultaneously reducing the numerical errors. In this paper, we make the first step to apply this framework to the differential equations of image processing. We focus on the Hamilton-Jacobi equation governing dilation and erosion processes which displays morphological symmetry, i.e. is invariant under strictly monotonically increasing transformations of gray-values. Results demonstrate that invariantization is able to handle the specific needs of differential equations applied in image processing, and thus encourage further research in this direction.
this article provides a review of existing methods for addressing the curse of dimensionality and analyzes current algorithms for modeling space from a single image using neural networks. Additionally, a proposed exte...
详细信息
暂无评论