Results 1  10
of
17
A Perceptually Motivated Online Benchmark for Image Matting
"... The availability of quantitative online benchmarks for lowlevel vision tasks such as stereo and optical flow has led to significant progress in the respective fields. This paper introduces such a benchmark for image matting. There are three key factors for a successful benchmarking system: (a) a ch ..."
Abstract

Cited by 29 (4 self)
 Add to MetaCart
(Show Context)
The availability of quantitative online benchmarks for lowlevel vision tasks such as stereo and optical flow has led to significant progress in the respective fields. This paper introduces such a benchmark for image matting. There are three key factors for a successful benchmarking system: (a) a challenging, highquality ground truth test set; (b) an online evaluation repository that is dynamically updated with new results; (c) perceptually motivated error functions. Our new benchmark strives to meet all three criteria. We evaluated several matting methods with our benchmark and show that their performance varies depending on the error function. Also, our challenging test set reveals problems of existing algorithms, not reflected in previously reported results. We hope that our effort will lead to considerable progress in the field of image matting, and welcome the reader to visit our benchmark at www.alphamatting.com. 1.
Fast matting using large kernel matting laplacian matrices
 In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
"... Abstract Image matting is of great importance in both computer vision and graphics applications. Most existing stateoftheart techniques rely on large sparse matrices such as the matting Laplacian [12]. However, solving these linear systems is often timeconsuming, which is unfavored for the us ..."
Abstract

Cited by 19 (1 self)
 Add to MetaCart
(Show Context)
Abstract Image matting is of great importance in both computer vision and graphics applications. Most existing stateoftheart techniques rely on large sparse matrices such as the matting Laplacian [12]. However, solving these linear systems is often timeconsuming, which is unfavored for the user interaction. In this paper, we propose a fast method for high quality matting. We first derive an efficient algorithm to solve a large kernel matting Laplacian. A large kernel propagates information more quickly and may improve the matte quality. To further reduce running time, we also use adaptive kernel sizes by a KDtree trimap segmentation technique. A variety of experiments show that our algorithm provides high quality results and is 5 to 20 times faster than previous methods. 1.
Improving Color Modeling for Alpha Matting
"... This paper addresses the problem of extracting an alpha matte from a single photograph given a userdefined trimap. A crucial part of this task is the color modeling step where for each pixel the optimal alpha value, together with its confidence, is estimated individually. This forms the data term o ..."
Abstract

Cited by 10 (2 self)
 Add to MetaCart
(Show Context)
This paper addresses the problem of extracting an alpha matte from a single photograph given a userdefined trimap. A crucial part of this task is the color modeling step where for each pixel the optimal alpha value, together with its confidence, is estimated individually. This forms the data term of the objective function. It comprises of three steps: (i) Collecting a candidate set of potential fore and background colors; (ii) Selecting high confidence samples from the candidate set; (iii) Estimating a sparsity prior to remove blurry artifacts. We introduce novel ideas for each of these steps and show that our approach considerably improves over stateoftheart techniques by evaluating it on a large database of 54 images with known highquality ground truth. 1
Energy Minimization Under Constraints on Label Counts
"... Many computer vision problems such as object segmentation or reconstruction can be formulated in terms of labeling a set of pixels or voxels. In certain scenarios, we may know the number of pixels or voxels which can be assigned to a particular label. For instance, in the reconstruction problem, w ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
Many computer vision problems such as object segmentation or reconstruction can be formulated in terms of labeling a set of pixels or voxels. In certain scenarios, we may know the number of pixels or voxels which can be assigned to a particular label. For instance, in the reconstruction problem, we may know size of the object to be reconstructed. Such label count constraints are extremely powerful and have recently been shown to result in good solutions for many vision problems. Traditional energy minimization algorithms used in vision cannot handle label count constraints. This paper proposes a novel algorithm for minimizing energy functions under constraints on the number of variables which can be assigned to a particular label. Our algorithm is deterministic in nature and outputs εapproximate solutions for all possible counts of labels. We also develop a variant of the above algorithm which is much faster, produces solutions under almost all label count constraints, and can be applied to all submodular quadratic pseudoboolean functions. We evaluate the algorithm on the twolabel (foreground/background) image segmentation problem and compare its performance with the stateoftheart parametric maximum flow and maxsum diffusion based algorithms. Experimental results show that our method is practical and is able to generate impressive segmentation results in reasonable time.
Y.: Nonlocal matting
, 2011
"... This work attempts to considerably reduce the amount of user effort in the natural image matting problem. The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramati ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
(Show Context)
This work attempts to considerably reduce the amount of user effort in the natural image matting problem. The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramatically reduce the number of pixels a user needs to manually label. We show how to avoid making the user provide redundant and unnecessary input, develop a method for clustering the image pixels for the user to label, and a method to perform highquality matte extraction. We show that this algorithm is therefore faster, easier, and higher quality than state of the art methods. 1.
A Spatially Varying PSFbased Prior for Alpha Matting
"... In this paper we considerably improve on a stateoftheart alpha matting approach by incorporating a new prior which is based on the image formation process. In particular, we model the prior probability of an alpha matte as the convolution of a highresolution binary segmentation with the spatially ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
(Show Context)
In this paper we considerably improve on a stateoftheart alpha matting approach by incorporating a new prior which is based on the image formation process. In particular, we model the prior probability of an alpha matte as the convolution of a highresolution binary segmentation with the spatially varying point spread function (PSF) of the camera. Our main contribution is a new and efficient deconvolution approach that recovers the prior model, given an approximate alpha matte. By assuming that the PSF is a kernel with a single peak, we are able to recover the binary segmentation with an MRFbased approach, which exploits flux and a new way of enforcing connectivity. The spatially varying PSF is obtained via a partitioning of the image into regions of similar defocus. Incorporating our new prior model into a stateoftheart matting technique produces results that outperform all competitors, which we confirm using a publicly available benchmark. 1.
Automatic RealTime Video Matting Using TimeofFlight Camera and Multichannel Poisson Equations
"... Abstract This paper presents an automatic realtime video matting system. The proposed system consists of two novel components. In order to automatically generate trimaps for live videos, we advocate a TimeofFlight (TOF) camerabased approach to video bilayer segmentation. Our algorithm combines co ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Abstract This paper presents an automatic realtime video matting system. The proposed system consists of two novel components. In order to automatically generate trimaps for live videos, we advocate a TimeofFlight (TOF) camerabased approach to video bilayer segmentation. Our algorithm combines color and depth cues in a probabilistic fusion framework. The scene depth information returned by the TOF camera is less sensitive to environment changes, which makes our method robust to illumination variation, dynamic background and camera motion. For the second step, we perform alpha matting based on the segmentation Electronic supplementary material The online version of this article (doi:10.1007/s112630110471x) contains supplementary material, which is available to authorized users.
Estimation of Alpha Mattes for Multiple Image Layers
"... Abstract—Image matting deals with the estimation of the alpha matte at each pixel, i.e., the contribution of the foreground and background objects to the composition of the image at that pixel. Existing methods for image matting are typically limited to estimating the alpha mattes for two image laye ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
(Show Context)
Abstract—Image matting deals with the estimation of the alpha matte at each pixel, i.e., the contribution of the foreground and background objects to the composition of the image at that pixel. Existing methods for image matting are typically limited to estimating the alpha mattes for two image layers only. However, in several applications one is interested in editing images with multiple objects. In this work, we consider the problem of estimating the alpha mattes of multiple (n 2) image layers. We show that this problem can be decomposed into n simpler subproblems of alpha matte estimation for two image layers. Moreover, we show that, by construction, the estimated alpha mattes at each pixel are constrained to sum up to 1 across the multiple image layers. A key feature of our framework is that the alpha mattes can be estimated in closed form. We further show that, due to the nature of spatial regularization used in the estimation, the final estimated alpha mattes are not constrained to take values in 0; 1Š. Hence, we study the optimization problem of estimating the alpha mattes for multiple image layers subject to the fact that the alpha mattes are nonnegative and sum up to 1 at each pixel. We present experiments to show that our proposed method can be used to extract mattes of multiple image layers. Index Terms—Image matting, alpha matte, multiple layers, matting Laplacian, superposition principle. Ç 1
Uncertainty Driven Multiscale Energy Minimization
"... This paper proposes a new multiscale energy minimization algorithm which can be used to efficiently solve large scale labelling problems in computer vision. The basic modus operandi of any multiscale method involves the construction of a smaller problem which can be solved efficiently. The solutio ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
This paper proposes a new multiscale energy minimization algorithm which can be used to efficiently solve large scale labelling problems in computer vision. The basic modus operandi of any multiscale method involves the construction of a smaller problem which can be solved efficiently. The solution of this problem is used to obtain a partial labelling of the original energy function, which in turn allows us to minimize it by solving its (much smaller) projection. We propose the use of new techniques for both the construction of the smaller problem, and the extraction of a partial solution. We demonstrate our method on the problem of interactive image segmentation. Traditional multiscale approaches for segmentation extract a partial solution using an image band around the boundaries of the object segmentation obtained by minimizing the smaller problem. This strategy fails on objects with fine structures and complex topologies. In contrast, our novel approach uses a minmarginal based uncertainty measure which allows us to handle such objects. Experiments show that our techniques result in solutions with low pixel labelling error. Furthermore, they take the same or less amount of computation compared to traditional multiscale techniques. 1.