An iterative optimization approach for unified image segmentation and matting

By Jue Wang, Michael F. Cohen. 2005

368 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Optimization & Training

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

In Optimization & Training

Citations in the corpus

Extreme Clicking for Efficient Object Annotation (2017, background): “[39, 51, 68]) and on which pixels are clamped to be object/backgound.”
A Closed-Form Solution to Natural Image Matting (2006, methodology): “Images (a,c,e,g,i,k,m,o) are taken from [19].”
Training Object Class Detectors from Eye Tracking Data (2014, neutral): “In traditional work using similar energy models [4,38,49], estimating the appearance models requires user interaction to indicate the image region containing the object (typically a manually drawn bounding-box or scribbles).”
ImageNet Auto-Annotation with Segmentation Propagation (2014, background): “Many works using analog energy functions [53,7,10,72] require user interaction to estimate the appearance model, typically a manually drawn bounding-box or scribbles.”
A global sampling method for alpha matting (2011, methodology): “Many papers [14, 18] argue that for a large sample set it is important to represent the frequency or probability of the samples.”
KNN Matting (2013, neutral): “Earlier, the iterative optimization [26] also directly made use of the compositing equation with known alpha in their foreground and background layer estimation.”
Image and Video Matting: A Survey (2007, neutral): “…and synthesis • Illumination and reflectance modeling • Shape Representation • Tracking • Calibration • Structure from motion • Motion estimation and registration • Stereo matching and reconstruction • 3D reconstruction and image-based modeling • Learning and statistical methods •…”
Optimized Color Sampling for Robust Matting (2007, methodology): “We compare the performances of 7 algorithms: Bayesian matting [1], Belief Propagation matting [14], Global Poisson matting [12], Random Walk matting [5], KnockOut 2 [2], closed-form matting [7], and the robust algorithm proposed in this paper.”
Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and Matting (2009, methodology): “13 (Color online) Variable width band working in conjunction with (Wang and Cohen 2005).”
Figure-ground segmentation by transferring window masks (2012, methodology): “For this, all masks in Nk are resized to the size of Wk in both their width and height dimensions.”
The patch transform and its applications to image editing (2008, methodology): “Our patch transform approach tries to side-step other typical image editing tasks, such as region selection [21] and object placement or blending [18, 22, 28].”
Interactive local adjustment of tonal values (2006, background): “2004], as well as for alpha matting [Wang and Cohen 2005].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, background): “[39, 51, 68]) and on which pixels are clamped to be object/backgound.”
Segmentation Propagation in ImageNet (2012, neutral): “Both [35, 36] and other works using analog energy functions [26, 37] require user interaction to estimate the appearance model, typically a manually drawn bounding-box or scribbles.”
Spectral Matting (2007, methodology): “This ability might signiﬁcantly improve matting algorithms which make use of color models such as [15].”