The Experts below are selected from a list of 204105 Experts worldwide ranked by ideXlab platform
Nikos Paragios - One of the best experts on this subject based on the ideXlab platform.
-
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
2018Co-Authors: Zhixin Shu, Mihir Sahasrabudhe, Rıza Güler, Dimitris Samaras, Nikos Paragios, Iasonas KokkinosAbstract:In this work we introduce Deforming Autoencoders, a generative model for Images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system ('template') and an Observed Image, while appearance is modeled in 'canonical', template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise Image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark local-ization. A more powerful form of unsupervised disentangling becomes possible in template coordinates, allowing us to successfully decompose face Images into shading and albedo, and further manipulate face Images. Latent Representation Input Image Generated Deformation Generated Texture Decoder Decoder Spatial Warping Reconstructed Image Encoder Fig. 1. Deforming Autoencoders follow the deformable template paradigm and model Image generation through a cascade of appearance (or, 'texture') synthesis in a canonical coordinate system and a spatial deformation that warps the texture to the Observed Image coordinates. By keeping the latent vector for texture short the network is forced to model shape variability through the deformation branch, so as to minimize a reconstruction loss. This allows us to train a deep gen-erative Image model that disentangles shape and appearance in an entirely unsupervised manner.
-
deforming autoencoders unsupervised disentangling of shape and appearance
European Conference on Computer Vision, 2018Co-Authors: Mihir Sahasrabudhe, Dimitris Samaras, Nikos Paragios, Riza Alp Guler, Iasonas KokkinosAbstract:In this work we introduce Deforming Autoencoders, a generative model for Images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (‘template’) and an Observed Image, while appearance is modeled in deformation-invariant, template coordinates. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise Image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark localization. We also achieve a more powerful form of unsupervised disentangling in template coordinates, that successfully decomposes face Images into shading and albedo, allowing us to further manipulate face Images.
-
Spatio-temporal speckle reduction in ultrasound sequences
Inverse Problems and Imaging, 2010Co-Authors: Noura Azzabou, Nikos ParagiosAbstract:In this paper we will propose a novel variational framework for speckle removal in ultrasound Images. Our method combines efficiently a fidelity to data term adapted to the Rayleigh distribution of the speckle and a novel spatio- temporal smoothness constraint. The regularization relies on a non parametric Image model that describes the Observed Image structure and express inter-dependencies between pixels in space and time. The interaction between pixels is determined through the definition of new measure of similarity between them to better reflect Image content. To compute this similarity measure, we take into consideration the spatial aspect as well as the temporal one. Experiments were carried on both synthetic and real data and the results show the potential of our method.
-
Spatio-temporal speckle reduction in ultrasound sequences
Lecture Notes in Computer Science, 2008Co-Authors: Noura Azzabou, Nikos ParagiosAbstract:In this paper we will be concerned with speckle removal in ultrasound Images. To this end, we introduce a new spatio-temporal de-noising method based on a variational formulation. The regularization relies on a non parametric Image model that describes the Observed Image structure and express inter-dependencies between pixels in space and time. Furthermore, we introduce a new data term adapted to the Rayleigh distribution of the speckle. The interaction between pixels is determined through the definition of new measure of similarity between them to better reflect Image content. To compute this similarity measure, we take into consideration the spatial aspect as well as the temporal one. Experiments were carried on both synthetic and real data and the results show the potential of our method.
Stanley Osher - One of the best experts on this subject based on the ideXlab platform.
-
Non-Local Retinex---A Unifying Framework and Beyond
SIAM Journal on Imaging Sciences, 2015Co-Authors: Dominique Zosso, Giang Tran, Stanley OsherAbstract:In this paper, we provide a short review of Retinex and then present a unifying framework. The fundamental assumption of all Retinex models is that the Observed Image is a multiplication between the illumination and the true underlying reflectance of the object. Starting from Morel's 2010 PDE model, where illumination is supposed to vary smoothly and where the reflectance is thus recovered from a hard-thresholded Laplacian of the Observed Image in a Poisson equation, we define our unifying Retinex model in two similar, but more general, steps. We reinterpret the gradient thresholding model as variational models with sparsity constraints. First, we look for a filtered gradient that is the solution of an optimization problem consisting of two terms: a sparsity prior of the reflectance and a fidelity prior of the reflectance gradient to the Observed Image gradient. Second, since this filtered gradient almost certainly is not a consistent Image gradient, we then fit an actual reflectance gradient to it, subje...
-
Computational Imaging - A unifying retinex model based on non-local differential operators
Computational Imaging XI, 2013Co-Authors: Dominique Zosso, Giang Tran, Stanley OsherAbstract:In this paper, we present a unifying framework for retinex that is able to reproduce many of the existing retinex implementations within a single model. The fundamental assumption, as shared with many retinex models, is that the Observed Image is a multiplication between the illumination and the true underlying reflectance of the object. Starting from Morel’s 2010 PDE model for retinex, where illumination is supposed to vary smoothly and where the reflectance is thus recovered from a hard-thresholded Laplacian of the Observed Image in a Poisson equation, we define our retinex model in similar but more general two steps. First, look for a filtered gradient that is the solution of an optimization problem consisting of two terms: The first term is a sparsity prior of the reflectance, such as the TV or H1 norm, while the second term is a quadratic fidelity prior of the reflectance gradient with respect to the Observed Image gradients. In a second step, since this filtered gradient almost certainly is not a consistent Image gradient, we then look for a reflectance whose actual gradient comes close. Beyond unifying existing models, we are able to derive entirely novel retinex formulations by using more interesting non-local versions for the sparsity and fidelity prior. Hence we define within a single framework new retinex instances particularly suited for texture-preserving shadow removal, cartoon-texture decomposition, color and hyperspectral Image enhancement.
-
VLSM - Global minimization of the active contour model with TV-Inpainting and two-phase denoising
Lecture Notes in Computer Science, 2005Co-Authors: Shingyu Leung, Stanley OsherAbstract:The active contour model [8,9,2] is one of the most well-known variational methods in Image segmentation. In a recent paper by Bresson et al. [1], a link between the active contour model and the variational denoising model of Rudin-Osher-Fatemi (ROF) [10] was demonstrated. This relation provides a method to determine the global minimizer of the active contour model. In this paper, we propose a variation of this method to determine the global minimizer of the active contour model in the case when there are missing regions in the Observed Image. The idea is to turn off the L1-fidelity term in some subdomains, in particular the regions for Image inpainting. Minimizing this energy provides a unified way to perform Image denoising, segmentation and inpainting.
Noura Azzabou - One of the best experts on this subject based on the ideXlab platform.
-
Spatio-temporal speckle reduction in ultrasound sequences
Inverse Problems and Imaging, 2010Co-Authors: Noura Azzabou, Nikos ParagiosAbstract:In this paper we will propose a novel variational framework for speckle removal in ultrasound Images. Our method combines efficiently a fidelity to data term adapted to the Rayleigh distribution of the speckle and a novel spatio- temporal smoothness constraint. The regularization relies on a non parametric Image model that describes the Observed Image structure and express inter-dependencies between pixels in space and time. The interaction between pixels is determined through the definition of new measure of similarity between them to better reflect Image content. To compute this similarity measure, we take into consideration the spatial aspect as well as the temporal one. Experiments were carried on both synthetic and real data and the results show the potential of our method.
-
Spatio-temporal speckle reduction in ultrasound sequences
Lecture Notes in Computer Science, 2008Co-Authors: Noura Azzabou, Nikos ParagiosAbstract:In this paper we will be concerned with speckle removal in ultrasound Images. To this end, we introduce a new spatio-temporal de-noising method based on a variational formulation. The regularization relies on a non parametric Image model that describes the Observed Image structure and express inter-dependencies between pixels in space and time. Furthermore, we introduce a new data term adapted to the Rayleigh distribution of the speckle. The interaction between pixels is determined through the definition of new measure of similarity between them to better reflect Image content. To compute this similarity measure, we take into consideration the spatial aspect as well as the temporal one. Experiments were carried on both synthetic and real data and the results show the potential of our method.
Iasonas Kokkinos - One of the best experts on this subject based on the ideXlab platform.
-
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
2018Co-Authors: Zhixin Shu, Mihir Sahasrabudhe, Rıza Güler, Dimitris Samaras, Nikos Paragios, Iasonas KokkinosAbstract:In this work we introduce Deforming Autoencoders, a generative model for Images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system ('template') and an Observed Image, while appearance is modeled in 'canonical', template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise Image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark local-ization. A more powerful form of unsupervised disentangling becomes possible in template coordinates, allowing us to successfully decompose face Images into shading and albedo, and further manipulate face Images. Latent Representation Input Image Generated Deformation Generated Texture Decoder Decoder Spatial Warping Reconstructed Image Encoder Fig. 1. Deforming Autoencoders follow the deformable template paradigm and model Image generation through a cascade of appearance (or, 'texture') synthesis in a canonical coordinate system and a spatial deformation that warps the texture to the Observed Image coordinates. By keeping the latent vector for texture short the network is forced to model shape variability through the deformation branch, so as to minimize a reconstruction loss. This allows us to train a deep gen-erative Image model that disentangles shape and appearance in an entirely unsupervised manner.
-
deforming autoencoders unsupervised disentangling of shape and appearance
European Conference on Computer Vision, 2018Co-Authors: Mihir Sahasrabudhe, Dimitris Samaras, Nikos Paragios, Riza Alp Guler, Iasonas KokkinosAbstract:In this work we introduce Deforming Autoencoders, a generative model for Images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (‘template’) and an Observed Image, while appearance is modeled in deformation-invariant, template coordinates. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise Image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark localization. We also achieve a more powerful form of unsupervised disentangling in template coordinates, that successfully decomposes face Images into shading and albedo, allowing us to further manipulate face Images.
Su Wang - One of the best experts on this subject based on the ideXlab platform.
-
An EM Approach to MAP Solution of Segmenting Tissue Mixtures: A Numerical Analysis
IEEE transactions on medical imaging, 2009Co-Authors: Zhengrong Liang, Su WangAbstract:This work presents an iterative expectation-maximization (EM) approach to the maximum a posteriori (MAP) solution of segmenting tissue mixtures inside each Image voxel. Each tissue type is assumed to follow a normal distribution across the field-of-view (FOV). Furthermore, all tissue types are assumed to be independent from each other. Under these assumptions, the summation of all tissue mixtures inside each voxel leads to the Image density mean value at that voxel. The summation of all the tissue mixtures' unobservable random processes leads to the Observed Image density at that voxel, and the Observed Image density value also follows a normal distribution (Image data are Observed to follow a normal distribution in many applications). By modeling the underlying tissue distributions as a Markov random field across the FOV, the conditional expectation of the posteriori distribution of the tissue mixtures inside each voxel is determined, given the Observed Image data and the current-iteration estimation of the tissue mixtures. Estimation of the tissue mixtures at next iteration is computed by maximizing the conditional expectation. The iterative EM approach to a MAP solution is achieved by a finite number of iterations and reasonable initial estimate. This MAP-EM framework provides a theoretical solution to the partial volume effect, which has been a major cause of quantitative imprecision in medical Image processing. Numerical analysis demonstrated its potential to estimate tissue mixtures accurately and efficiently.
