Vectorising Bitmaps into Semi‐Transparent Gradient Layers

We present an interactive approach for decompositing bitmap drawings and studio photographs into opaque and semi‐transparent vector layers. Semi‐transparent layers are especially challenging to extract, since they require the inversion of the non‐linear compositing equation. We make this problem tractable by exploiting the parametric nature of vector gradients, jointly separating and vectorising semi‐transparent regions. Specifically, we constrain the foreground colours to vary according to linear or radial parametric gradients, restricting the number of unknowns and allowing our system to efficiently solve for an editable semi‐transparent foreground. We propose a progressive workflow, where the user successively selects a semi‐transparent or opaque region in the bitmap, which our algorithm separates as a foreground vector gradient and a background bitmap layer. The user can choose to decompose the background further or vectorise it as an opaque layer. The resulting layered vector representation allows a variety of edits, such as modifying the shape of highlights, adding texture to an object or changing its diffuse colour.

[1]  David A. Forsyth,et al.  A Subdivision-Based Representation for Vector Image Editing , 2012, IEEE Transactions on Visualization and Computer Graphics.

[2]  P. Selinger Potrace : a polygon-based tracing algorithm , 2003 .

[3]  Yizhou Yu,et al.  Patch-based image vectorization with automatic curvilinear feature alignment , 2009, SIGGRAPH 2009.

[4]  Assaf Zomet,et al.  Separating reflections from a single image using local features , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[5]  Ralph R. Martin,et al.  Vectorizing Cartoon Animations , 2009, IEEE Transactions on Visualization and Computer Graphics.

[6]  Frédo Durand,et al.  A visibility algorithm for converting 3D meshes into editable 2D vector graphics , 2009, ACM Trans. Graph..

[7]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[8]  Brendt Wohlberg,et al.  Efficient Minimization Method for a Generalized Total Variation Functional , 2009, IEEE Transactions on Image Processing.

[9]  Tom Duff,et al.  Compositing digital images , 1984, SIGGRAPH.

[10]  David Bommes,et al.  Practical Mixed-Integer Optimization for Geometry Processing , 2010, Curves and Surfaces.

[11]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[12]  Pascal Barla,et al.  Diffusion curves: a vector representation for smooth-shaded images , 2008, ACM Trans. Graph..

[13]  Adrien Bousseau,et al.  Depicting stylized materials with vector shade trees , 2013, ACM Trans. Graph..

[14]  Ralph R. Martin,et al.  Automatic and topology-preserving gradient mesh generation for image vectorization , 2009, SIGGRAPH 2009.

[15]  Michael S. Brown,et al.  Single Image Layer Separation Using Relative Smoothness , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Lorenz T. Biegler,et al.  On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming , 2006, Math. Program..

[17]  James F. Blinn,et al.  Blue screen matting , 1996, SIGGRAPH.

[18]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Ralph R. Martin,et al.  Automatic and topology-preserving gradient mesh generation for image vectorization , 2009, ACM Trans. Graph..

[20]  Michael F. Cohen,et al.  Image and Video Matting: A Survey , 2007, Found. Trends Comput. Graph. Vis..

[21]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[22]  Assaf Zomet,et al.  Learning to Perceive Transparency from the Statistics of Natural Scenes , 2002, NIPS.

[23]  David Salesin,et al.  Stylized Vector Art from 3D Models with Region Support , 2008, Comput. Graph. Forum.

[24]  William A. Barrett,et al.  Object-based vectorization for interactive image editing , 2006, The Visual Computer.

[25]  Bruno Lévy,et al.  Ardeco: automatic region detection and conversion , 2006, EGSR '06.

[26]  Harry Shum,et al.  Image vectorization using optimized gradient meshes , 2007, ACM Trans. Graph..

[27]  Michael S. Brown,et al.  Matting and compositing of transparent and refractive objects , 2011, TOGS.

[28]  Nancy S. Pollard,et al.  Real-time gradient-domain painting , 2008, SIGGRAPH 2008.

[29]  E. Adelson Perceptual organization and the judgment of brightness. , 1993, Science.