Lazy snapping

By Yin Li, Jian Sun, Chi-Keung Tang, Harry Shum. 2004

1,278 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

FocalClick: Towards Practical Interactive Image Segmentation (2022, background): “Moreover, it causes unexpected changes that are far away from the user clicks.”
Deep Interactive Object Selection (2016, methodology): “Strokebased methods are popular, and use a number of underlying algorithms, including normalized cuts [22], graph cut [2, 11, 26], geodesics [1, 4], the combination of graph cut and geodesics [20, 9] and random walks [8].”
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation (2016, methodology): “Among various forms of user interactions, scribbles are particularly popular [4, 17, 11, 16, 19, 6] and have been recognized as a user-friendly way of interacting.”
A comparative evaluation of interactive segmentation algorithms (2010, neutral): “The “GrabCut” algorithm [7] and the “Lazy Snapping” algorithm [16] are two such variants developed by Microsoft.”
MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input (2019, methodology): “Interactive Image Segmentation: Early interactive image segmentation methods mainly exploit boundary properties for segmentation [17, 29] while more recent approaches are based on graphical models, such as graph cut [4, 21, 33], random walker [11] and geodesic approaches [2, 7, 31].”
Semantic colorization with internet images (2011, methodology): “To colorize a grayscale image, the user first segments the foreground object(s) with the powerful and intuitive Lazy Snapping technique [Li et al. 2004], and provides a semantic text label for each object.”
A survey of graph theoretical approaches to image segmentation (2013, methodology): “Segmentation results of GC [57], IGC [69], LS [81] and RW [32] with the same input seeds.”
Medical Image Segmentation Methods, Algorithms, and Applications (2014, methodology): “Some segmentation methods have been generated based on the graph cut like grab cut [98] and lazy snapping [99].”
iLamps: geometrically aware and self-configuring projectors (2003, methodology): “A related area of work is that of object “cut and paste”, where mattes are computed after performing binary segmentation with minimal user input [Rother et al. 2004; Li et al. 2004].”
Conditional Diffusion for Interactive Segmentation (2021, methodology): “Human could provide bounding boxes [26, 30, 15], scribbles [16, 6, 1], or clicks [27, 20, 32, 11] to express the segmentation intentions, which guide the algorithm for the mask extraction process.”
Error-Tolerant Scribbles Based Interactive Image Segmentation (2014, background): “Among various interactive approaches, two of the most popular ones are the boundary-based segmentation[9] and the scribble-based segmentation[11, 12, 1, 6, 8, 7].”
F-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation (2020, methodology): “[17] use graph-cut algorithm to separate foreground pixels from the background using distances from each pixel to foreground and background seeds in color space.”
A Comparative Study of Energy Minimization Methods for Markov Random Fields (2006, methodology): “Our benchmark consists of a segmentation problem, inspired by the interactive segmentation algorithm of [12] or its more recent extensions [13, 14].”
Deepstrip: High-Resolution Boundary Refinement (2020, methodology): “Conventional methods like dense Conditional Random Fields (CRF) [21], Graph Cuts [8] model the relationship between nearby pixels and thus can be applied to reﬁne LR masks [23].”
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation (2014, methodology): “Li et al. proposed Lazy Snapping [22] which separates the segmentation into an object marking step and a boundary editing step.”
Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis (2009, methodology): “…homepage: www.e lsev ier .com/ locate /pr Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis Zhouchen Lina,∗, Junfeng Heb, Xiaoou Tanga, Chi-Keung Tangb aMicrosoft Research, Asia, Zhichun Road #49, Haidian District, Beijing 100190, PR China…”