“Highly Accurate GPU-Accelerated Animation Rigs for Toothless” by Sooi and Genzwürker
Conference:
Type(s):
Title:
- Highly Accurate GPU-Accelerated Animation Rigs for Toothless
Session/Category Title:
- Character Animation Make Some Noise
Presenter(s)/Author(s):
Moderator(s):
Abstract:
Real-time feedback of character rigs is an important feature for every animator. While improvements to the execution engine in Maya helped to run character rigs in parallel and therefore faster, it was still impossible to use high-quality character rigs directly during the animation stage. Instead, low-quality proxy rigs had to be created to give the animators instant feedback, but with the drawback of providing low-quality deformation results. This paper describes a solution to run our high-quality character deformation chains on the GPU, allowing artists to visualize render-quality animation in the viewport. We will explain how we ported less GPU-suitable algorithms, such as BVH, to the GPU while achieving the same results accurately. This drastically reduced the need to create proxy rigs while simultaneously providing animators a high-fidelity user experience.
References:
[1] Autodesk. 2022. Using Parallel Maya. https://download.autodesk.com/us/company/files/UsingParallelMaya/2022/UsingParallelMaya.html
[2] Philippe Helluy. 2011. A portable implementation of the radix sort algorithm in OpenCL. (May 2011). https://hal.science/hal-00596730 working paper or preprint.
[3] John Kahwaty, Walter Yoder, Andy Lin, Gene S. Lee, and David Suroviec. 2019. Optimizing rig manipulation with GPU and parallel evaluation. In ACM SIGGRAPH 2019 Talks (Los Angeles, California) (SIGGRAPH ’19). Association for Computing Machinery, New York, NY, USA, Article 63, 2 pages.
[4] Tero Karras. 2012. Maximizing parallelism in the construction of BVHs, octrees, and k-d trees. In Proceedings of the Fourth ACM SIGGRAPH / Eurographics Conference on High-Performance Graphics (Paris, France) (EGGH-HPG’12). Eurographics Association, Goslar, DEU, 33–37.
[5] Tzon-Tzer Lu and Sheng-Hua Shiou. 2002. Inverses of 2 × 2 block matrices. Computers & Mathematics with Applications 43, 1 (2002), 119–129.
[6] Petro J. Martin, Luis F. Ayuso, Roberto Torres, Roberto, and Antonio Gavilanes. 2012. Algorithmic strategies for optimizing the parallel reduction primitive in CUDA. In Proceedings of the Fourth ACM SIGGRAPH / Eurographics Conference on High-Performance Graphics (Madrid, Spain) (EGGH-HPG’12). IEEE, New York, US, 511–519.
[7] Matthias Müller, Jan Bender, Nuttapong Chentanez, and Miles Macklin. 2016. A robust method to extract the rotational part of deformations. In Proceedings of the 9th International Conference on Motion in Games (Burlingame, California) (MIG ’16). Association for Computing Machinery, New York, NY, USA, 55–60.
[8] Manne Öhrström, Leo Hills, and Theodore Jones. 2021. FIRA – Portable Realtime Rig Deformation. In Proceedings of the 2021 Digital Production Symposium (Virtual Event, USA) (DigiPro ’21). Association for Computing Machinery, New York, NY, USA, Article 2, 3 pages.
[9] Karl Rupp, Philippe Tillet, Florian Rudolf, Josef Weinbub, Andreas Morhammer, Tibor Grasser, Ansgar Jüngel, and Siegfried Selberherr. 2016. ViennaCL—Linear Algebra Library for Multi- and Many-Core Architectures. SIAM Journal on Scientific Computing 38, 5 (2016), S412–S439.
