Timothy Costigan
Rachel McDonnell
ABSTRACT
For real-time applications, blendshape animations are usually calculated on the CPU, which are slow to animate, and are therefore generally limited to only the closest level of detail for a small number of characters in a scene. In this paper, we present a GPU based blendshape animation technique. By storing the blendshape model (including animations) on the GPU, we are able to attain significant speed improvements over CPU-based animation. We also find that by using compute shaders to decouple rendering and animation we can improve performance when rendering a crowd animation. Further gains are also made possible by using a smaller subset of blendshape expressions, at the cost of expressiveness. However, the quality impact can be minimised by selecting this subset carefully. We discuss a number of potential metrics to automate this selection.
Supplemental Material
Available for Download
- Aspert, N., Santa Cruz, D., and Ebrahimi, T. 2002. MESH: measuring errors between surfaces using the Hausdorff distance. In ICME (1), 705--708.Google Scholar
- Deng, Z., and Noh, J. 2008. Computer facial animation: A survey. In Data-driven 3D facial animation. Springer, 1--28.Google Scholar
- Dudash, B. 2007. Skinned instancing. Tech. rep., NVidia.Google Scholar
- Ekman, P., and Friesen, W. V. 1978. Facial action coding system. Consulting Psychologists Press, Stanford University.Google Scholar
- Evans, C., Martinsson, L., and Herfort, S. 2014. Building an empire: asset production in Ryse. In ACM SIGGRAPH 2014 Courses, 18. Google ScholarDigital Library
- Faceware, 2016. Faceware Technologies Inc. http://facewaretech.com/.Google Scholar
- Garland, M., and Heckbert, P. S. 1997. Surface simplification using quadric error metrics. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques, 209--216. Google ScholarDigital Library
- Harte, N., and Gillen, E. 2015. TCD-TIMIT: An audio-visual corpus of continuous speech. IEEE Transactions on Multimedia 17, 5, 603--615.Google ScholarDigital Library
- Lewis, J., and Anjyo, K.-i. 2010. Direct manipulation blend-shapes. IEEE Computer Graphics and Applications, 4, 42--50. Google ScholarDigital Library
- Lewis, J. P., Anjyo, K., Rhee, T., Zhang, M., Pighin, F., and Deng, Z. 2014. Practice and Theory of Blendshape Facial Models. In Eurographics 2014 - State of the Art Reports.Google Scholar
- Lorach, T. 2007. DirectX 10 Blend Shapes: Breaking the Limits. GPU Gems 3, Addison-Wesley Professional, ch. 3, 53--67.Google Scholar
- McDonnell, R., Larkin, M., Dobbyn, S., Collins, S., and O'Sullivan, C. 2008. Clone attack! perception of crowd variety. ACM Transactions on Graphics (TOG) 27, 3, 26. Google ScholarDigital Library
- Mohr, A., and Gleicher, M. 2003. Deformation sensitive decimation. Tech. rep., University of Wisconsin Graphics Group.Google Scholar
- Pilgrim, S., Steed, A., and Aguado, A. 2007. Progressive skinning for character animation. Computer Animation and Virtual Worlds 18, 4--5, 473--481. Google ScholarDigital Library
- Segal, M., and Akeley, K. 2012. The OpenGL Graphics System: A Specification (Version 4.3 (Core Profile)). Tech. rep., Khronos Group.Google Scholar
- Seo, J., Irving, G., Lewis, J. P., and Noh, J. 2011. Compression and Direct Manipulation of Complex Blendshape Models. In Proceedings of the 2011 SIGGRAPH Asia Conference, 164:1--164:10. Google ScholarDigital Library
- Seol, Y., Seo, J., Kim, P. H., Lewis, J. P., and Noh, J. 2011. Artist friendly facial animation retargeting. In ACM Transactions on Graphics (TOG), 162. Google ScholarDigital Library
- Seol, Y., Lewis, J., Seo, J., Choi, B., Anjyo, K., and Noh, J. 2012. Spacetime expression cloning for blendshapes. ACM Transactions on Graphics (TOG) 31, 2, 14. Google ScholarDigital Library
- Wang, Z., Bovik, A. C., Sheikh, H. R., and Simoncelli, E. P. 2004. Image quality assessment: from error visibility to structural similarity. Image Processing, IEEE Transactions on 13, 4, 600--612. Google ScholarDigital Library
- Yee, H. 2004. Perceptual metric for production testing. Journal of Graphics Tools 9, 4, 33--40.Google ScholarCross Ref
Index Terms
- Improving blendshape performance for crowds with GPU and GPGPU techniques
Recommendations
Semantically-aware blendshape rigs from facial performance measurements
SA '16: SIGGRAPH ASIA 2016 Technical BriefsWe present a framework for automatically generating personalized blendshapes from actor performance measurements, while preserving the semantics of a template facial animation rig. Firstly, we capture various poses from the subject with our ...
Reducing blendshape interference by selected motion attenuation
I3D '05: Proceedings of the 2005 symposium on Interactive 3D graphics and gamesBlendshapes (linear shape interpolation models) are perhaps the most commonly employed technique in facial animation practice. A major problem in creating blendshape animation is that of blendshape interference: the adjustment of a single blendshape "...
Performance-driven animation of hand-drawn cartoon faces
We present a novel performance-driven approach to animating cartoon faces starting from pure 2D drawings. A 3D approximate facial model automatically built from front and side view master frames of character drawings is introduced to enable the animated ...
Comments