GraphDeco

VideoDoodles: Hand-Drawn Animations on Videos with Scene-Aware Canvases
Presentation | Team members | Collaborations | Publications | Job offers | Contact

 

VideoDoodles: Hand-Drawn Animations on Videos with Scene-Aware Canvases

Emilie Yu, Kevin Blackburn-Matzen, Cuong Nguyen, Oliver Wang, Rubaiat Habib Kazi, Adrien Bousseau
ACM Transactions on Graphics (SIGGRAPH Conference Proceedings), Volume 42, Number 4 - Aug 2023
Download the publication : VideoDoodles.pdf [48.1Mo]  
We present an interactive system to ease the creation of so-called video doodles – videos on which artists insert hand-drawn animations for entertainment or educational purposes. Video doodles are challenging to create because to be convincing, the inserted drawings must appear as if they were part of the captured scene. In particular, the drawings should undergo tracking, perspective deformations and occlusions as they move with respect to the camera and to other objects in the scene – visual effects that are difficult to reproduce with existing 2D video editing software. Our system supports these effects by relying on planar canvases that users position in a 3D scene reconstructed from the video. Furthermore, we present a custom tracking algorithm that allows users to anchor canvases to static or dynamic objects in the scene, such that the canvases move and rotate to follow the position and direction of these objects. When testing our system, novices could create a variety of short animated clips in a dozen of minutes, while professionals praised its speed and ease of use compared to existing tools.

Images and movies

teaser.png [544Ko]
 

See also




See the project page for additional content.

Acknowledgements and Funding

We thank our study participants for their time and effort, Wilmot Li for inspiration all along the project, Pascal Tempier for infrastructure support, Nicolas Rosset for help with testing the user interface, Felix Hähnlein, Timothée De Graeve, Rubaiat Habib and his daughters for appearing in or providing input footage. We thank the content creators of all tutorials cited in Supplemental Materials for sharing valuable information on how to make video doodles, and we thank LeopARTnik, Joseph Diaz and @murtsell for inspiring us and permitting usage of their creations as examples in the accompagnying video. We thank the anonymous reviewers for their helpful comments. This work was supported by ERC Starting Grant D3 (ERC-2016-STG 714221), and by software and research donations from Adobe.

BibTex references

@Article{YBNWKB23,
  author       = "Yu, Emilie and Blackburn-Matzen, Kevin and Nguyen, Cuong and Wang, Oliver and Kazi, Rubaiat Habib and Bousseau, Adrien",
  title        = "VideoDoodles: Hand-Drawn Animations on Videos with Scene-Aware Canvases",
  journal      = "ACM Transactions on Graphics (SIGGRAPH Conference Proceedings)",
  number       = "4",
  volume       = "42",
  month        = "Aug",
  year         = "2023",
  keywords     = "video editing, motion design, interface, video depth",
  url          = "http://www-sop.inria.fr/reves/Basilic/2023/YBNWKB23"
}

Other publications in the database

» Emilie Yu
» Adrien Bousseau