Stochastic completion fields: a neural model of illusory contour shape and salience

Williams, Lance R.; Jacobs, David W.

doi:10.1109/iccv.1995.466910

Cited by 155 publications

(178 citation statements)

References 18 publications

Supporting

Mentioning

176

Contrasting

Order By: Relevance

“…[22,7,28], ex planations for why they are seen at all are of two sorts. One class of explanation treats the image itself as the primary object of interest, which it is the visual system's job to elaborate and refine.…”

Section: Introductionmentioning

confidence: 99%

Perceptual Organization of Occluding Contours of Opaque Surfaces

Saund¹

1999

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Perceptual Organization of Occluding Contours of Opaque Surfaces

Saund¹

1999

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…In fact, some methods incorporate low-, mid-, and high-level shape priors, as exemplified by Ren et al [7]. We will also stop short of reviewing methods focused solely on contour completion, e.g., Ren et al [8] and Williams and Jacobs [9], although the regularities exploited by such approaches can clearly play a powerful role in detecting closure.…”

Section: Related Workmentioning

confidence: 99%

Optimal Contour Closure by Superpixel Grouping

Levinshtein

Sminchisescu

Dickinson

2010

Computer Vision – ECCV 2010

View full text Add to dashboard Cite

Abstract. Detecting contour closure, i.e., finding a cycle of disconnected contour fragments that separates an object from its background, is an important problem in perceptual grouping. Searching the entire space of possible groupings is intractable, and previous approaches have adopted powerful perceptual grouping heuristics, such as proximity and co-curvilinearity, to manage the search. We introduce a new formulation of the problem, by transforming the problem of finding cycles of contour fragments to finding subsets of superpixels whose collective boundary has strong edge support in the image. Our cost function, a ratio of a novel learned boundary gap measure to area, promotes spatially coherent sets of superpixels. Moreover, its properties support a global optimization procedure using parametric maxflow. We evaluate our framework by comparing it to two leading contour closure approaches, and find that it yields improved performance.

show abstract

“…In order to have a dense anisotropic field, one needs to extend the anisotropy over the whole domain using some kind of interpolation. This notion of interpolation of local orientations is similar to the computation of good continuation field, as studied for instance in stochastic completion fields [16] or tensor voting [17]. In this paper, we propose a simple interpolation method that computes a dense tensor field with a linear diffusion outside a region of high confidence.…”

Section: Design Of An Anisotropic Tensor Field the Riemannian Metricmentioning

confidence: 99%

Anisotropic Geodesics for Perceptual Grouping and Domain Meshing

Bougleux

Peyré

Cohen

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper shows how Voronoi diagrams and their dual Delaunay complexes, defined with geodesic distances over 2D Reimannian manifolds, can be used to solve two important problems encountered in computer vision and graphics. The first problem studied is perceptual grouping which is a curve reconstruction problem where one should complete in a meaningful way a sparse set of noisy curves. From this latter curves, our grouping algorithm first designs an anisotropic tensor field that corresponds to a Reimannian metric. Then, according to this metric, the Delaunay graph is constructed and pruned in order to correctly link together salient features. The second problem studied is planar domain meshing, where one should build a good quality triangulation of a given domain. Our meshing algorithm is a geodesic Delaunay refinement method that exploits an anisotropic tensor field in order to locally impose the orientation and aspect ratio of the created triangles.

show abstract

Stochastic completion fields: a neural model of illusory contour shape and salience

Cited by 155 publications

References 18 publications

Perceptual Organization of Occluding Contours of Opaque Surfaces

Perceptual Organization of Occluding Contours of Opaque Surfaces

Optimal Contour Closure by Superpixel Grouping

Anisotropic Geodesics for Perceptual Grouping and Domain Meshing

Contact Info

Product

Resources

About