Interactive graph cut based segmentation with shape priors

By Daniel Freedman, Zhang Tao. 2005

464 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

Reviving Iterative Training with Mask Guidance for Interactive Segmentation (2021, methodology): “Scribble-based methods often use heuristic and complicated procedures for simulating user input, which makes it hard to fairly evaluate them [5, 6, 7].”
Extreme Clicking for Efficient Object Annotation (2017, methodology): “To reduce annotation time many interactive segmentation techniques have been proposed, which require the user to input either a bounding box around the object [42, 51, 71], or scribbles [3, 16, 24, 26, 27, 42, 50, 64, 65, 72], or clicks [31, 69].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, methodology): “To reduce annotation time many interactive segmentation techniques have been proposed, which require the user to input either a bounding box around the object [42, 51, 71], or scribbles [3, 16, 24, 26, 27, 42, 50, 64, 65, 72], or clicks [31, 69].”
Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision (2014, methodology): “[14] combined MRFs and deformable models, [10] utilize a template with a levelset formulation, and [37] incorporate shape priors computed from deformable part-based models in holistic scene understanding.”
Regional Interactive Image Segmentation Networks (2017, unknown): “To further improve the performance, shape priors such as [9, 25, 7, 12] have been considered in the literature.”
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation (2014, background): “While fully automated segmentation is arguably an intrinsically ambiguous problem [5] and manual segmentation is time-consuming to obtain, semi-automated (user-interactive) segmentation has demonstrated great practical importance and popularity [10, 32, 15, 9, 22, 29, 19, 8, 35, 27, 20].”
GrabCut in One Cut (2013, methodology): “Several prior methods rely on graph-cut based segmentation with shape prior [21, 8, 14, 23].”
Star Shape Prior for Graph-Cut Image Segmentation (2008, methodology): “The advantage of using a generic star shape prior is that it can be directly incorporated in the optimization procedure, no expensive registration between the model and the image, like in [26, 27] is required.”
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes (2009, background): “argued that threshold-based detection results can be improved by incorporating more sophisticated models, like human shape priors, we maintain that such models can be used to augment our track segmentation approach (see [14] for a use of shape priors in graph cuts-based segmentation).”