Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and Matting

By Xue Bai, Guillermo Sapiro. 2009

326 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

Deep Extreme Cut: From Extreme Points to Object Segmentation (2017, neutral): “3 Geodesic matting [2] > 20 > 20 45.”
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].”
Deep Interactive Object Selection (2016, methodology): “Bai and Sapiro [1] present a new algorithm that computes weighted geodesic distances to the user-provided scribbles.”
Interactive Image Segmentation With First Click Attention (2020, methodology): “[3] both applied geodesic distance for optimization in interactive image segmentation.”
Regional Interactive Image Segmentation Networks (2017, unknown): “Bai and Sapiro [1] classified each pixel into foreground and background based on weighted geodesic distances.”
Interactive Image Segmentation with Latent Diversity (2018, methodology): “We compare the presented approach to a number of well-known interactive image segmentation models: graph cuts [4], random walks [12], geodesic matting [2], Euclidean star convexity [13], and geodesic star convexity [13].”
Streaming Hierarchical Video Segmentation (2012, unknown): “Many driving applications in video, such as animation [7, 8], require a dense segmentation that feature-based methods cannot naturally provide.”
Learning to segment under various forms of weak supervision (2015, methodology): “Supervision in the form of partial labels has been effectively utilized in interactive object segmentation via graph-cuts [3], random walks [12], geodesic shortest path [2], and geodesic star convexity [15].”
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].”
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation (2014, methodology): “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].”
Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections (2019, methodology): “[46], DAVIS [40] and Berkeley [37]. 2. Related Work Interactive Object Segmentation. Traditional methods model interactive segmentation as an energy minimization problem on a graph deﬁned over pixels [12,46,7,24,41]. User inputs are used to create an image-speciﬁc appearance model based on low-level”
Geodesic star convexity for interactive image segmentation (2010, unknown): “It is also possible to use gradients in the likelihood image to get rid of texture edges as done in [2].”
Geodesic Object Proposals (2014, methodology): “As described in Section 3, we can extract a small set of high-quality object proposals by identifying certain critical level sets of the SGDT. Proposals formed by these critical level sets are shown in Figure 2e.”