max planck institut informatik
mpii logo Minerva of the Max Planck Society

Animated 3D Creatures from Single-view Video by Skeletal Sketching Graphics Interface 2016


Animated 3D Creatures from Single-view Video by Skeletal Sketching

Bernhard Reinert1     Tobias Ritschel2     Hans-Peter Seidel1    

MPI Informatik1, University College London2


Our approach analyzes 2D sketches (colored strokes) over some key frames (columns) of a 2D video to produce an animated and textured 3D mesh (bottom row).


Abstract

Extraction of deformable 3D geometry is not accessible to casual users, as it either requires dedicated hardware or vast manual effort. Inspired by the recent success of semi-automatic 3D reconstruction from a single image, we introduce a sketch-based extraction technique that allows a fast reconstruction of a dynamic articulated shape from a single video. We model the shape as a union of generalized cylinders deformed by an animation of their axes, representing the "limbs" of the articulated shape. The axes are acquired from strokes sketched by the user on top of a few key frames. Our method bypasses the meticulous effort required to establish dense correspondences when applying common structure from motion techniques for shape reconstruction. Instead, we produce a plausible shape from the fusion of silhouettes over multiple frames. Reconstruction is performed at interactive rates, allowing interaction and refinement until the desired quality is achieved.

Video

Downloads

Paper Full Quality (62.6 MB) or Compressed (2.3 MB)
Video (73.7 MB)
GI 2016 presentation slides (135.7 MB).

Citation

Bernhard Reinert, Tobias Ritschel, Hans-Peter Seidel
Animated 3D Creatures from Single-view Video by Skeletal Sketching
Graphics Interface 2016.

@inproceedings{Reinert:2016:AnimatedCreatures,
  author = { 
	Bernhard Reinert and
	Tobias Ritschel and 
	Hans-Peter Seidel},
  title = {Animated 3D Creatures from Single-view Video by Skeletal Sketching},
  booktitle = {GI '16: Proceedings of the 42st Graphics Interface Conference},
  year = {2016}
}

Acknowledgements

We would like to thank the anonymous reviewers for helpful comments. Videos courtesy of National Geographic and BBC Worldwide.