Scale-invariant contour completion using conditional random fields

By Xiaofeng Ren, Charless C. Fowlkes, Jitendra Malik. 2005

150 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Probabilistic & Bayesian Methods

Citations in the corpus

Fast Edge Detection Using Structured Forests (2014, background): “Unfortunately, many visually salient edges do not correspond to color gradients, such as texture edges [34] and illusory contours [39].”
Crisp Boundary Detection Using Pointwise Mutual Information (2014, methodology): “More modern methods include a Conditional Random Field (CRF) presented in [20], which builds a probabilistic model for the completion problem, and uses loopy belief propagation to infer the closed contours.”
A Particle Filter Framework for Contour Detection (2012, methodology): “[8] proposed a curvilinear continuity stochastic approach by modeling piecewise linear approximations of contours and employed a constrained Delaunay triangulation which tends to fill the gaps between the detections.”
Supervised Learning of Edges and Object Boundaries (2006, methodology): “[15] build graphs to reinforce some mid-level cues to give more complete edges.”
Structured Forests for Fast Edge Detection (2013, background): “Unfortunately, many visually salient edges do not correspond to color gradients, such as texture edges [24] and illusory contours [29].”
From contours to regions: An empirical evaluation (2009, background): “There have been significant advances in contour detection in the last few years [16] [37] [27] [12] [48] [22] [36].”
Multi-scale Improves Boundary Detection in Natural Images (2008, background): “68, higher than most existing results on the Berkeley benchmark [22, 23, 11, 24, 25, 12].”
Semantic contours from inverse detectors (2011, background): “For example, grouping edge pixels based on mid-level Gestalt cues, e.g. [18] [23] [12], or recovering occlusion boundaries from a single image [11], or from a sequence [21].”
utomation of 3 D reconstruction of neural tissue from large volume of onventional serial section transmission electron micrographs (2008, background): “The average fraction of neuronal processes in one EM section hat will lead to ambiguity then may be estimated as 1(h) = 〈fambiguous(d)〉 = ∫ 2h 0 (d)fambiguous(d) dd, (7) here we take the average of the fraction of ambiguous profiles for iven neuronal process size d over the distribution of the…”
Beyond pixels: exploring new representations and applications for motion analysis (2009, methodology): “Similar local and global modeling of contour saliency was proposed in [86]; in [73], both edge saliency and curvilinear continuity were used to extract closed contours from static images.”
Segmentation of Natural Images by Texture and Boundary Compression (2010, unknown): “There are several methods that can be used to obtain a superpixel initialization, including those of Mori et al. (2004), Felzenszwalb & Huttenlocher (2004), and Ren et al. (2005).”
Contour Detection and Hierarchical Image Segmentation (2011, methodology): “Though much of the extensive literature on contour detection predates its development, the BSDS [2] has since found wide acceptance as a benchmark for this task [23], [24], [25], [26], [27], [28], [35], [61].”
Using contours to detect and localize junctions in natural images (2008, background): “A thinned, real-valued contour image can be obtained from gPb by considering the maximal response over orientations at each location and applying non-maximum suppression [3, 12].”
Figure/Ground Assignment in Natural Images (2006, methodology): “It has been previously applied to image labeling [20, 21], as well as contour completion [16].”
Generalized Boundaries from Multiple Image Interpretations (2012, unknown): “[39] 0.”