Loading...

SIGGRAPH 2013 - Implicit Skinning: Real-Time Skin Deformation with Contact Modeling

231,199 views

Loading...

Loading...

Transcript

The interactive transcript could not be loaded.

Loading...

Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on May 11, 2013

Edit: Go see our latest work: https://www.youtube.com/watch?v=GyOww...

This is the video accompanying our SIGGRAPH 2013 research paper: "Implicit Skinning: Real-Time Skin Deformation with Contact Modeling"

More on the official Implicit Skinning project's page:
http://rodolphe-vaillant.fr/permalink...

Related work on blending operators:
https://vimeo.com/57928521
https://vimeo.com/25365676

---------------------------------------------------------------------------------------------
Remarks:

This work is a RESEARCH project this means:

- Implicit Skinning is implemented as a CUDA standalone application there is currently no plugins for Blender, 3DSmax, Maya or else. However if you are interested by this technology we are open to collaborations (contact us for more details http://rodolphe-vaillant.fr, http://www.irit.fr/~Loic.Barthe/)

- 90% of the programming and rendering work was done by a single person whose never been specifically trained for any artistic work
(there is of course a team doing the theoretical research;
3D characters and long animations at the end are provided by third parties)

---------------------------------------------------------------------------------------------
Technical summary:
We present Implicit Skinning a real time method for character skinning. The technique is a post process applied over a geometric skinning (such as linear blending or dual-quaternions) which handles the self-collisions of the limbs by producing skin contact effects and plausible organic bulges in real-time. In addition we avoid the usual collapsing or bulging artifacts seen with linear blending or dual quaternions at the skeleton's joint.

To achieve these effects we need a volumetric representation of the mesh. Implicit Skinning's idea is to use a set of implicit surfaces (3D distance-fields/scalar-fields), rather than tetrehadral/voxel mesh and a slow physical simulation. For each limb, we automatically generate the implicit surface shape, and use it to adjust the position of the geometric skinning's vertices without loss of details.

As Implicit Skinning acts as a post-process, it fits well into the standard animation pipeline. Moreover, it requires no intensive computation step such as an explicit collision detection between triangles, and therefore provides real-time performances. Currently the Implicit Skinning algorithm is implemented on a standalone application and the core of the computation is parallelized per vertex on GPU with CUDA.

---------------------------------------------------------------------------------------------
Authors:
Rodolphe Vaillant(1,2), Loïc Barthe(1), Gaël Guennebaud(3), Marie-Paule Cani(4),
Damien Rhomer(5), Brian Wyvill(6), Olivier Gourmel(1) and Mathias Paulin(1)

(1)IRIT - Université de Toulouse, (2)University of Victoria, (3)Inria Bordeaux,
(4)LJK - Grenoble Universités - Inria, (5)CPE Lyon - Inria

---------------------------------------------------------------------------------------------
Acknowledgments:
We thank artists, companies and universities who provided us with nice 3D models. Juna model comes from Rogério Perdiz. Dana and Carl models from the company MIXAMO. Finally the famous armadillo model comes from the Standford university 3D scan repository.

We also thank the blender foundation for providing everyone with the Blender software which we used to do some of the enhanced rendering in the video. Rendering setup is a modified version of the Sintel Lite rendering setup.

This work has been partially funded by the IM&M project http://www.irit.fr/~Loic.Barthe/imm.php (ANR-11-JS02-007) and the advanced grant EXPRESSIVE from the European Research council. Partial funding also comes from the Natural Sciences and Engineering Research Council of Canada, the GRAND NCE, Canada and Intel Corps. Finally, this work received partial support from the Royal Society Wolfson Research Merit Award.

Loading...

When autoplay is enabled, a suggested video will automatically play next.

Up next


to add this to Watch Later

Add to

Loading playlists...