Results 11  20
of
135
Surfaces with occlusions from layered stereo
 IEEE Trans. on PAMI
, 2004
"... Abstract—We propose a new binocular stereo algorithm that estimates scene structure as a collection of smooth surface patches. The disparities within each patch are modeled by a continuousvalued spline, while the extent of each patch is represented via a pixelwise partitioning of the images. Dispar ..."
Abstract

Cited by 76 (2 self)
 Add to MetaCart
Abstract—We propose a new binocular stereo algorithm that estimates scene structure as a collection of smooth surface patches. The disparities within each patch are modeled by a continuousvalued spline, while the extent of each patch is represented via a pixelwise partitioning of the images. Disparities and extents are alternately estimated in an iterative, energy minimization framework. Experimental results demonstrate that, for scenes consisting of smooth surfaces, the proposed algorithm significantly improves upon the state of the art. Index Terms—Binocular stereo vision, energy minimization, graph cuts, hybrid system, smooth surfaces, surface fitting, boundary localization, sharp discontinuities, quantitative comparison. 1
Manhattanworld Stereo
"... Multiview stereo (MVS) algorithms now produce reconstructions that rival laser range scanner accuracy. However, stereo algorithms require textured surfaces, and therefore work poorly for many architectural scenes (e.g., building interiors with textureless, painted walls). This paper presents a nove ..."
Abstract

Cited by 72 (7 self)
 Add to MetaCart
(Show Context)
Multiview stereo (MVS) algorithms now produce reconstructions that rival laser range scanner accuracy. However, stereo algorithms require textured surfaces, and therefore work poorly for many architectural scenes (e.g., building interiors with textureless, painted walls). This paper presents a novel MVS approach to overcome these limitations for Manhattan World scenes, i.e., scenes that consists of piecewise planar surfaces with dominant directions. Given a set of calibrated photographs, we first reconstruct textured regions using an existing MVS algorithm, then extract dominant plane directions, generate plane hypotheses, and recover perview depth maps using Markov random fields. We have tested our algorithm on several datasets ranging from office interiors to outdoor buildings, and demonstrate results that outperform the current state of the art for such texturepoor scenes. 1.
Piecewise Planar Stereo for Imagebased Rendering
"... We present a novel multiview stereo method designed for imagebased rendering that generates piecewise planar depth maps from an unordered collection of photographs. First a discrete set of 3D plane candidates are computed based on a sparse point cloud of the scene (recovered by structure from moti ..."
Abstract

Cited by 53 (7 self)
 Add to MetaCart
(Show Context)
We present a novel multiview stereo method designed for imagebased rendering that generates piecewise planar depth maps from an unordered collection of photographs. First a discrete set of 3D plane candidates are computed based on a sparse point cloud of the scene (recovered by structure from motion) and sparse 3D line segments reconstructed from multiple views. Next, evidence is accumulated for each plane using 3D point and line incidence and photoconsistency cues. Finally, a piecewise planar depth map is recovered for each image by solving a multilabel Markov Random Field (MRF) optimization problem using graphcuts. Our novel energy minimization formulation exploits highlevel scene information. It incorporates geometric constraints derived from vanishing directions, enforces free space violation constraints based on ray visibility of 3D points and 3D lines and imposes smoothness priors specific to planes that intersect. We demonstrate the effectiveness of our approach on a wide variety of outdoor and indoor datasets. The view interpolation results are perceptually pleasing, as straight lines are preserved and holes are minimized even for challenging scenes with nonLambertian and textureless surfaces. 1.
Spatially coherent clustering using graph cuts
 In CVPR (2
, 2004
"... Feature space clustering is a popular approach to image segmentation, in which a feature vector of local properties (such as intensity, texture or motion) is computed at each pixel. The feature space is then clustered, and each pixel is labeled with the cluster that contains its feature vector. A ma ..."
Abstract

Cited by 52 (1 self)
 Add to MetaCart
(Show Context)
Feature space clustering is a popular approach to image segmentation, in which a feature vector of local properties (such as intensity, texture or motion) is computed at each pixel. The feature space is then clustered, and each pixel is labeled with the cluster that contains its feature vector. A major limitation of this approach is that feature space clusters generally lack spatial coherence (i.e., they do not correspond to a compact grouping of pixels). In this paper, we propose a segmentation algorithm that operates simultaneously in feature space and in image space. We define an energy function over both a set of clusters and a labeling of pixels with clusters. In our framework, a pixel is labeled with a single cluster (rather than, for example, a distribution
A Layered Stereo Algorithm Using Image Segmentation And Global Visibility Constraints
 in IEEE International Conference on Image Processing
, 2004
"... We propose a new stereo algorithm which uses colour segmentation to allow the handling of large untextured regions and precise localization of depth boundaries. Each segment is modelled as a plane. Robustness of the depth representation is achieved by the use of a layered model. Layers are extracted ..."
Abstract

Cited by 44 (4 self)
 Add to MetaCart
(Show Context)
We propose a new stereo algorithm which uses colour segmentation to allow the handling of large untextured regions and precise localization of depth boundaries. Each segment is modelled as a plane. Robustness of the depth representation is achieved by the use of a layered model. Layers are extracted by meanshiftbased clustering of depth planes. For layer assignment a global cost function is defined. The quality of the disparity map is measured by warping the reference image to the second view and comparing it with the real image. Zbuffering enforces visibility and allows the explicit detection of occlusions. An efficient greedy algorithm searches for a local minimum of the cost function. Layer extraction and assignment are alternately applied. Results obtained for benchmark and selfrecorded images indicate that the proposed algorithm can compete with the stateoftheart.
Graph Cuts in Vision and Graphics: Theories and Applications
 “MATH. MODELS OF C.VISION: THE HANDBOOK”, EDTS. PARAGIOS, CHEN, FAUGERAS
"... Combinatorial mincut algorithms on graphs emerged as an increasingly useful tool for problems in vision. Typically, the use of graphcuts is motivated by one of the following two reasons. Firstly, graphcuts allow geometric interpretation; under certain conditions a cut on a graph can be seen as a ..."
Abstract

Cited by 38 (2 self)
 Add to MetaCart
Combinatorial mincut algorithms on graphs emerged as an increasingly useful tool for problems in vision. Typically, the use of graphcuts is motivated by one of the following two reasons. Firstly, graphcuts allow geometric interpretation; under certain conditions a cut on a graph can be seen as a hypersurface in ND space embedding the corresponding graph. Thus, many applications in vision and graphics use mincut algorithms as a tool for computing optimal hypersurfaces. Secondly, graphcuts also work as a powerful energy minimization tool for a fairly wide class of binary and nonbinary energies that frequently occur in early vision. In some cases graph cuts produce globally optimal solutions. More generally, there are iterative graphcut based techniques that produce provably good approximations which (were empirically shown to) correspond to highquality solutions in practice. Thus, another large group of applications use graphcuts as an optimization technique for lowlevel vision problems based on global energy formulations. This chapter is intended as a tutorial illustrating these two aspects of graphcuts in the context of problems in computer vision and graphics. We explain general theoretical properties that motivate the use of graph cuts, as well as, show their limitations.
Shape and the stereo correspondence problem
 International Journal of Computer Vision
, 2005
"... We examine the implications of shape on the process of finding dense correspondence and halfocclusions for a stereo pair of images. The desired property of the disparity map is that it should be a piecewise continuous function which is consistent with the images and which has the minimum number of ..."
Abstract

Cited by 36 (1 self)
 Add to MetaCart
(Show Context)
We examine the implications of shape on the process of finding dense correspondence and halfocclusions for a stereo pair of images. The desired property of the disparity map is that it should be a piecewise continuous function which is consistent with the images and which has the minimum number of discontinuities. To zeroth order, piecewise continuity becomes piecewise constancy. Using this approximation, we first discuss an approach for dealing with such a frontoparallel shapeless world, and the problems involved therein. We then introduce horizontal and vertical slant to create a first order approximation to piecewise continuity. In particular, we emphasize the following geometric fact: a horizontally slanted surface (i.e., having depth variation in the direction of the separation of the two cameras) will appear horizontally stretched in one image as compared to the other image. Thus, while corresponding two images, N pixels on a scanline in one image may correspond to a different number of pixels M in the other image. This leads to three important modifications to existing stereo algorithms: (a) due to unequal sampling, existing intensity matching metrics must be modified, (b) unequal numbers of pixels in the two images must be allowed to correspond to each other, and (c) the uniqueness constraint, which is often used for detecting occlusions, must be changed to an interval uniqueness constraint. We also discuss the asymmetry between vertical and horizontal slant, and the central role of nonhorizontal edges in the context of vertical slant. Using experiments, we discuss cases where existing algorithms fail, and how the incorporation of these new constraints provides correct results. 1.
A layered stereo matching algorithm using image segmentation and global visibility constraints
, 2005
"... ..."
(Show Context)
Regionbased progressive stereo matching
 In Conference on Computer Vision and Pattern Recognition
, 2004
"... A novel regionbased progressive stereo matching algorithm is presented. It combines the strengthes of previous regionbased and progressive approaches. The progressive framework avoids the time consuming global optimization, while the inherent problem, the sensitivity to early wrong decisions, is s ..."
Abstract

Cited by 34 (1 self)
 Add to MetaCart
(Show Context)
A novel regionbased progressive stereo matching algorithm is presented. It combines the strengthes of previous regionbased and progressive approaches. The progressive framework avoids the time consuming global optimization, while the inherent problem, the sensitivity to early wrong decisions, is significantly alleviated via the regionbased representation. A growinglike process matches the regions progressively using a global bestfirst strategy based on a cost function integrating disparity smoothness and visibility constraint. The performance on standard evaluation platform using various real images shows that the algorithm is among the stateoftheart both in accuracy and efficiency. 1.
Stereo correspondence with slanted surfaces: Critical implications of horizontal slant
 In Proc. CVPR
, 2004
"... We examine the stereo correspondence problem in the presence of slanted scene surfaces. In particular, we highlight a previously overlooked geometric fact: a horizontally slanted surface (i.e. having depth variation in the direction of the separation of the two cameras) will appear horizontally stre ..."
Abstract

Cited by 33 (4 self)
 Add to MetaCart
(Show Context)
We examine the stereo correspondence problem in the presence of slanted scene surfaces. In particular, we highlight a previously overlooked geometric fact: a horizontally slanted surface (i.e. having depth variation in the direction of the separation of the two cameras) will appear horizontally stretched in one image as compared to the other image. Thus, while corresponding two images, N pixels on a scanline in one image may correspond to a different number of pixels M in the other image. This leads to three important modifications to existing stereo algorithms: (a) due to unequal sampling, intensity matching metrics such as the popular BirchfieldTomasi procedure must be modified, (b) unequal numbers of pixels in the two images must be allowed to correspond to each other, and (c) the uniqueness constraint, which is often used for detecting occlusions, must be changed to a 3D uniqueness constraint. This paper discusses these new constraints and provides a simple scanline based matching algorithm for illustration. We experimentally demonstrate test cases where existing algorithms fail, and how the incorporation of these new constraints provides correct results. Experimental comparisons of the scanline based algorithm with standard data sets are also provided. 1.