A perceptually motivated online benchmark for image matting

By Christoph Rhemann, Carsten Rother, Jue Wang, Margrit Gelautz, Pushmeet Kohli, Pamela Rott. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009

411 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A global sampling method for alpha matting (2011, methodology): “The total runtime on the 27 benchmark images in [13] is 170 seconds for our method (sampling only).”
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (2017, methodology): “we use soft visibility maps, when the pixel p is visible both in I0 and I1, the network learns to adaptively combine the information from two images, similarly to the matting effect [24].”
KNN Matting (2013, neutral): “ison with CF and LB matting in [20] available in the online”
Deep Image Matting (2017, methodology): “2a), including the 27 training images from [25] and every fifth frame from the videos from [26].”
Fast cost-volume filtering for visual correspondence and beyond (2011, methodology): “Related to interactive segmentation, [11] adopted the guided ﬁ lter to compute a soft-segmentation, so called alpha matte [18].”
Geodesic star convexity for interactive image segmentation (2010, methodology): “The dataset (see Figure 10) consists of the GrabCut dataset (49 images) [1] augmented with images from the PASCAL VOC’09 segmentation challenge (99 images) [7] and 3 images from the alpha-matting dataset [17].”