Computer Laboratory

Past projects

Abstract

We introduce a novel video stylisation framework based on decomposing the video volume into 3D Voronoi cells. Colour samples are taken for each cell in a video, leading to an efficient and sparse video representation. Based on the same representation, our framework affords a wide variety of artistic rendering styles. We present two families of such styles for reconstructing stylised video frames: (1) using neighbouring Voronoi cells, and (2) a derived per-frame Delaunay-like triangulation. Our framework provides a flexible foundation for automatic video stylisation that is artistically expressive and temporally coherent.

Teaser figure Examples of our video stylisation approach using 200,000 Voronoi sites (0.16% of the video’s pixels): (a) the original video frame, (b) processed using our “patchwork” rendering style with average 2D cell colour, (c) processed using the same rendering style but now with average 3D cell colour, which causes “motion blur” artefacts. (click for larger version)

Downloads

Errata

  • The caption of Figure 3 (page 3) should read n, not k.
  • In equation 3 (page 4), dM is the Manhattan distance.

Bibtex

  @inproceedings{VoronoiVideoStylisation,
    author    = {Christian Richardt and Neil A. Dodgson},
    title     = {Voronoi Video Stylisation},
    booktitle = {Computer Graphics International Short Papers},
    month     = may,
    year      = {2009},
    pages     = {103--108},
    location  = {Victoria, British Columbia, Canada},
    url       = {http://www.cl.cam.ac.uk/research/rainbow/projects/voronoivideo/},
    doi       = {10.1145/1629739.1629752},
  }