Figure/Ground Assignment in Natural Images

By Xiaofeng Ren, Charless C. Fowlkes, Jitendra Malik. 2006

158 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Fast Edge Detection Using Structured Forests (2014, background): “For instance, [29] applies structured learning to the problem of semantic image labeling for which local image labels are also highly interdependent.”
Shape Sharing for Object Segmentation (2012, methodology): “A recent method for figure-ground contour classification discovers prototypical local geometric features, yet it depends on bottom-up cues alone when grouping the labels predicted by each local prototype [21].”
Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding (2015, background): “For example, image segmentation follows from edge detection [12, 1, 2, 7, 4]; figure/ground, occlusion, or depth layering follows from reasoning over discrete contours or regions [27, 16, 21, 36, 18] with some systems also reliant on motion cues [30, 15, 32, 31].”
Recovering Occlusion Boundaries from a Single Image (2007, methodology): “While these techniques have been mostly limited to line drawings, Ren et al. [19] have recently proposed a method for labeling occlusion boundaries in images of natural scenes.”
Boundary Detection Benchmarking: Beyond F-Measures (2013, background): “Many other works such as [21, 10, 3] also included pB (or gPB) boundary intensity in their feature design.”
Layered object detection for multi-class segmentation (2010, unknown): “, figure-ground cues[18] or geometric context[7]).”
SemiContour: A Semi-supervised Learning Approach for Contour Detection (2016, background): “Contours in local patches (denoted by sketch tokens [20]) contain rich and well-known patterns, including straight lines, parallel lines, curves, T-junctions, Y-junctions, etc [27, 20].”
Boundary Detection Using F-Measure-, Filter- and Feature- (F3) Boost (2010, result): “A similar result was preliminarily observed in [25] for the figure-ground assignment task, where geometric blur descriptors were used to leverage mid-level information.”
RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth (2021, methodology): “For reasoning occlusion relationship between objects, the dataset in [34] consists of 200 images, where boundaries are assigned with figure/ground labels.”
Recovering Occlusion Boundaries from an Image (2011, background): “This may partially explain why recent methods to infer figure/ground labels in natural images (Ren et al. 2006; Leichter and Lindenbaum 2009) tend to work much better for manually-provided boundaries than automatically detected boundaries.”
Structured Forests for Fast Edge Detection (2013, methodology): “They often contain well-known patterns, such as straight lines, parallel lines, T-junctions or Y-junctions [30] [21].”
LabelMe: Online Image Annotation and Applications (2010, methodology): “Finally, there are other recent relevant methods to recover geometric information for images [9], [19], [21], [33], [38], [46], [58], [67], [82].”
Learning Graphical Model Parameters with Approximate Marginal Inference (2013, methodology): “This “surrogate likelihood” [17] approximation appears to be the most widely used loss in imaging problems, with marginals approximated by either MNF [18], [19], TRW [20], or LBP [21], [22], [23], [24], [25].”
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context (2007, methodology): “Color potential parameters The color potentials are learned at test time for each image independently, using the approach of Rother et al. (2004). First, the color clusters (4) are learned in an unsupervised manner using K-means.”
Building a database of 3D scenes from user annotations (2009, methodology): “Also relevant are methods to recover geometric information from image information [27, 28, 14, 24, 34, 18, 9, 21, 37].”