Projects
Voronoi Video Stylisation
Computer Graphics International 2009 – Short Papers
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.
Downloads
- Paper (PDF, 8.0 MB)
- Comparison of all styles using average 2D cell colours (Xvid, 24.5 MB)
- Comparison of all styles using point-sampled cell colours (Xvid, 30.5 MB)
- Comparison of all styles using average 3D cell colours (Xvid, 22.9 MB)
- Comparison of different coverage settings (Xvid, 22.2 MB)
- The C++ source code for Avisynth is available on request.
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}, }