Bilayer Segmentation of Live Video

By Antonio Criminisi, Geoffrey Cross, Andrew Blake, Vladimir Kolmogorov. Computer Vision and Pattern Recognition, 2006

316 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/71a12fa1e1b3e47301ffedab91b89673ee86979d

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

Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and Matting (2009, methodology): “In Grady (2006), the author uses random walks for soft image segmentation (see also Grady et al. 2005 for the application of this to matting). Each pixel is assigned the label with maximal probability that a random walker reaches it when starting from the corresponding scribbles. The authors of Wang”
A Survey on Deep Learning Technique for Video Segmentation (2021, background): “They assume that the background is known a priori, and that the camera is stationary [25], [26] or undergoes a predictable, parametric 2D [27] or 3D motion with 3D parallax [28].”
Segmenting Salient Objects from Images and Videos (2010, methodology): “However, the first term adds lower cost for such segmentation boundaries that co-occur with contours of high image contrast [30].”
A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting (2007, background): “The Bilayer approach, [8], segments videos with basically static background.”
A Fully-Connected Layered Model of Foreground and Background Flow (2013, methodology): “While our 2-layer method is related to figure-ground segmentation, previous work in that area typically uses motion only as a cue to segmentation [7], treats it as an observation [2], and does not attempt to accurately estimate optical flow.”
Beyond pixels: exploring new representations and applications for motion analysis (2009, unknown): “The motion information of a video sequence is the key for video compression, 3D geometry reconstruction [116], object tracking [95], segmentation [30] and advanced video editing [94].”
GeoS: Geodesic Image Segmentation (2008, methodology): “The estimated CRF posterior ˜ p qN ( α ) is used in ﬁg.”
Video Segmentation by Non-Local Consensus voting (2014, background): “These were assumed to be either: (i) stationary backgrounds [5, 9, 12, 33] or backgrounds undergoing 2D parametric motion [16, 18, 30] (thus image registration can be used for background stabilization); or (ii) backgrounds undergoing 3D motions with 3D parallax [17, 34, 37].”