Christian Richardt^1,2    Jorge Lopez-Moreno^1,3    Adrien Bousseau¹    Maneesh Agrawala⁴    George Drettakis¹

¹ Inria       ² MPI Informatik       ³ URJC, Madrid       ⁴ University of California, Berkeley

Computer Graphics Forum (Proceedings of EGSR 2014)

---

Abstract

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.

Downloads

• Paper preprint (PDF, 6.5 MB)
• Supplemental video (MP4, 70 MB)
• Presentation slides (Keynote ’09, 18 MB) — PDF export of slides (16 MB)
• Ground-truth evaluation of our decompositing approach on synthetic images (ZIP, 13 MB)
• All of our input images and results as shown below (ZIP, 24 MB)

Bibtex

@article{LayeredVectorisation,
  author    = {Christian Richardt and Jorge Lopez-Moreno and Adrien Bousseau and Maneesh Agrawala and George Drettakis},
  title     = {Vectorising Bitmaps into Semi-Transparent Gradient Layers},
  journal   = {Computer Graphics Forum (Proceedings of EGSR)},
  year      = {2014},
  month     = {July},
  volume    = {33},
  number    = {4},
  pages     = {11--19},
  doi       = {10.1111/cgf.12408},
  url       = {http://richardt.name/layered-vectorisation/},
}

Vectorisation results