Spectral Matting

By Anat Levin, Alex Rav-Acha, Dani Lischinski. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

436 citations recorded by the source corpus.

We present spectral matting: a new approach to natural image matting that automatically computes a set of fundamental fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/23e811c0d4165b38aecbc27d6d0a525f0cc50f58

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 Industrial and Manufacturing Engineering

Citations in the corpus

User-Friendly Interactive Image Segmentation Through Unified Combinatorial User Inputs (2010, methodology): “while soft segmentation algorithms such as [3], [4] extract a fractional (fuzzy) matte for an image.”
KNN Matting (2013, neutral): “In CF matting [14], [15], the foreground and background are solved by using the estimated alpha and the compositing equation with a spatial coherence term.”
Image and Video Matting: A Survey (2007, neutral): “Volume 3 Issue 2, 2007”
A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting (2007, methodology): “The spectral matting technique, [10], automatically computes a set of soft matting components via a linear transformation of the smallest eigenvectors of the matting Laplacian matrix [12].”
Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and Matting (2009, methodology): “Figure 16 then presents comparisons with the work in Wang and Cohen (2005), Photoshop Extract Filter (ADOBE SYSTEMS INCORP 2002), Photoshop CS3 Quick Selection & Refine Edge tools (ADOBE SYSTEMS INCORP 2007), Corel Knockout2 (COREL CORPORATION 2002), Spectral Matting (Levin et al. 2007),12 and Power”
A perceptually motivated online benchmark for image matting (2009, methodology): “Then we computed error rates (mean squared error ) for all images with a variety of matting algorithms (i.e. [23] [14] [9] [20] [6] [8]).”
DeepProp: Extracting Deep Features from a Single Image for Edit Propagation (2016, background): “…use several types of weighting coefﬁcients φ ij that represent relations between neighbor pixels, such as the afﬁnity function [LLW04] based on similarity of pixel values based on similarity of pixel values (when considering pixel gradient information) and matting Laplacian [LRAL07] for matting.”
Exemplar-Based Face Parsing (2013, methodology): “The hair mattes from [11] are usually accurate, but mistakes are inevitable.”
Real-Time High-Resolution Background Matting (2020, background): “Traditional (non-learning based) matting algorithms [6, 16, 17, 29, 9, 2, 7] require manual annotation (a trimap) and solve for the alpha matte in the ‘unknown’ region of the trimap.”
An Augmented Lagrangian Method for Total Variation Video Restoration (2011, neutral): “Image source: [39].”