Christian Richardt1,2    Jorge Lopez-Moreno1,3    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

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

‘cup’ photo

Select image to be shown on the left:

Downloads:

‘glass’ photo

Select image to be shown on the left:

Downloads:

‘high-heels’ photo

  • Source: Shutterstock/Picsfive
  • Preprocessing: reflection removed and downsampled 1200×923 pixels
  • Postprocessing: manual cleanup and snapping of region boundaries

Select image to be shown on the left:

Downloads:

‘lens’ photo

  • Source: Flickr/Dino Quinzani (CC BY-SA 2.0)
  • Preprocessing: downsampled and cropped to 529×529 pixels

Select image to be shown on the left:

Downloads:

‘wine’ photo

Select image to be shown on the left:

Downloads:

‘hoover’ drawing

Select image to be shown on the left:

Downloads:

‘purair’ drawing

Select image to be shown on the left:

Downloads:

‘cone’ vector drawing

  • Source: own drawing based on tutorial by Jasmina Stanojevic
  • Preprocessing: rasterised at resolution 552×436 pixels
  • Postprocessing: manual cleanup and snapping of region boundaries

Select image to be shown on the left:

Downloads: