Interactive painterly stylization of images, videos and 3D animations

Jingwan Lu, Pedro V. Sander, Adam Finkelstein

Research output: Chapter in Book/Report/Conference proceedingConference contribution

41 Scopus citations

Abstract

We introduce a real-time system that converts images, video, or 3D animation sequences to artistic renderings in various painterly styles. The algorithm, which is entirely executed on the GPU, can efficiently process 512 resolution frames containing 60,000 individual strokes at over 30 fps. In order to exploit the parallel nature of GPUs, our algorithm determines the placement of strokes entirely from local pixel neighborhood information. The strokes are rendered as point sprites with textures. Temporal coherence is achieved by treating the brush strokes as particles and moving them based on optical flow. Our system renders high quality results while allowing the user interactive control over many stylistic parameters such as stroke size, texture and density.

Original languageEnglish (US)
Title of host publicationProceedings of I3D 2010
Subtitle of host publicationThe 2010 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
Pages127-134
Number of pages8
DOIs
StatePublished - 2010
Event2010 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2010 - Washington, DC, United States
Duration: Feb 19 2010Feb 21 2010

Publication series

NameProceedings of I3D 2010: The 2010 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games

Other

Other2010 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2010
Country/TerritoryUnited States
CityWashington, DC
Period2/19/102/21/10

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Keywords

  • GPU processing
  • Non-photorealistic rendering
  • Painterly rendering
  • Particle systems
  • Video processing

Fingerprint

Dive into the research topics of 'Interactive painterly stylization of images, videos and 3D animations'. Together they form a unique fingerprint.

Cite this