Segmenting the image into an arbitrary number of parts is at the core of image understanding. Many formulations of the task have been suggested over the years. Among these are axiomatic functionals, which are hard to ...
详细信息
Surface reconstruction using patch-based multi-view stereo commonly assumes that the underlying surface is locally planar. this is typically not true so that least-squares fitting of a planar patch leads to systematic...
详细信息
Osmosis filters are based on drift-diffusion processes. they offer nontrivial steady states with a number of interesting applications. In this paper we present a fully discrete theory for linear osmosis filtering that...
详细信息
Blind deconvolution involves the estimation of a sharp signal or image given only a blurry observation. Because this problem is fundamentally ill-posed, strong priors on boththe sharp image and blur kernel are requir...
详细信息
Very recently we have proposed to use a complex Ginzburg-Landau equation for high contrast inpainting, to restore higher dimensional (volumetric) data (which has applications in frame interpolation), improving sparsel...
详细信息
Very recently we have proposed to use a complex Ginzburg-Landau equation for high contrast inpainting, to restore higher dimensional (volumetric) data (which has applications in frame interpolation), improving sparsely sampled data and to fill in fragmentary surfaces. In this paper we review digital inpainting algorithms and compare their performance with a Ginzburg-Landau inpainting model. For the solution of the Ginzburg-Landau equation we compare the performance of several numerical algorithms. A stability and convergence analysis is given and the consequences for applications to digital inpainting are discussed.
Very recently we have proposed to use a complex Ginzburg-Landau equation for high contrast inpainting, to restore higher dimensional (volumetric) data (which has applications in frame interpolation), improving sparsel...
详细信息
Very recently we have proposed to use a complex Ginzburg-Landau equation for high contrast inpainting, to restore higher dimensional (volumetric) data (which has applications in frame interpolation), improving sparsely sampled data and to fill in fragmentary surfaces. In this paper we review digital inpainting algorithms and compare their performance with a Ginzburg-Landau inpainting model. For the solution of the Ginzburg-Landau equation we compare the performance of several numerical algorithms. A stability and convergence analysis is given and the consequences for applications to digital inpainting are discussed.
We propose a novel variational approach based on a level set formulation of the Mumford-Shah functional and shape priors. We extend the functional by a labeling function which indicates image regions in which the shap...
详细信息
ISBN:
(纸本)354040368X
We propose a novel variational approach based on a level set formulation of the Mumford-Shah functional and shape priors. We extend the functional by a labeling function which indicates image regions in which the shape prior is enforced. By minimizing the proposed functional with respect to boththe level set function and the labeling function, the algorithm selects image regions where it is favorable to enforce the shape prior. By this, the approach permits to segment multiple independent objects in an image, and to discriminate familiar objects from unfamiliar ones by means of the labeling function. Numerical results demonstrate the performance of our approach.
We present a novel variational approach to dense motion estimation of highly non-rigid structures in image sequences. Our representation of the motion vector field is based on the extended Helmholtz Decomposition into...
详细信息
ISBN:
(纸本)354040368X
We present a novel variational approach to dense motion estimation of highly non-rigid structures in image sequences. Our representation of the motion vector field is based on the extended Helmholtz Decomposition into its principal constituents: the laminar flow and two potential functions related to the solenoidal and irrotational flow, respectively. the potential functions, which are of primary interest for flow pattern analysis in numerous application fields like remote sensing or fluid mechanics, are directly estimated from image sequences with a variational approach. We use regularizers with derivatives up to third order to obtain unbiased high-quality solutions. Computationally, the approach is made tractable by means of auxiliary variables. the performance of the approach is demonstrated with ground-truth experiments and real-world data.
the proceedings contain 56 papers. the special focus in this conference is on Deep Structure Representation, scalespace Mathematics, Equivalences, Implementing scalespaces and Other Evolution Equations. the topics i...
ISBN:
(纸本)354040368X
the proceedings contain 56 papers. the special focus in this conference is on Deep Structure Representation, scalespace Mathematics, Equivalences, Implementing scalespaces and Other Evolution Equations. the topics include: Many-to-many matching of scale-space feature hierarchies using metric embedding;content based image retrieval using multiscale top points;feature coding with a statistically independent cortical representation;scale-space image analysis based on hermite polynomials theory;a complete system of measurement invariants for abelian lie transformation groups;equivalence results for TV diffusion and TV regularisation;correspondences between wavelet shrinkage and nonlinear diffusion;a generalized discrete scale-space formulation for 2-d and 3-d signals;real-time scale selection in hybrid multi-scale representations;a scalespace for contour registration using minimal surfaces;the maximum principle for Beltrami color flow;the monogenic scalespace on a bounded domain and its applications;least squares and robust estimation of local image structure;mode estimation using pessimistic scalespace tracking;properties of Brownian image models in scale-space;image decomposition application to SAR images;basic morphological operations, band-limited images and sampling;an explanation for the logarithmic connection between linear and morphological systems;interest point detection and scale selection in space-time;towards recognition-based variational segmentation using shape priors and dynamic labeling;a Markov random field approach to multi-scale shape analysis and regularizing a set of unstructured 3d points from a sequence of stereo images.
暂无评论