ABSTRACT
In animation production, animators always spend significant time and efforts to develop quality deformation systems for characters with complex appearances and details. In order to decrease the time spent repetitively skinning and fine-tuning work, we propose an end-to-end approach to automatically compute deformations for new characters based on existing graph information of high-quality skinned character meshes. We adopt the idea of regarding mesh deformations as a combination of linear and nonlinear parts and propose a novel architecture for approximating complex nonlinear deformations. Linear deformations on the other hand are simple and therefore can be directly computed, although not precisely. To enable our network handle complicated graph data and inductively predict nonlinear deformations, we design the graph-attention-based (GAT) block to consist of an aggregation stream and a self-reinforced stream in order to aggregate the features of the neighboring nodes and strengthen the features of a single graph node. To reduce the difficulty of learning huge amount of mesh features, we introduce a dense connection pattern between a set of GAT blocks called “dense module” to ensure the propagation of features in our deep frameworks. These strategies allow the sharing of deformation features of existing well-skinned character models with new ones, which we call densely connected graph attention network (DenseGATs). We tested our DenseGATs and compared it with classical deformation methods and other graph-learning-based strategies. Experiments confirm that our network can predict highly plausible deformations for unseen characters.
- Nesreen K. Ahmed, Ryan A. Rossi, Rong Zhou, John Boaz Lee, Xiangnan Kong, Theodore L. Willke, and Hoda Eldardiry. 2017. Inductive Representation Learning in Large Attributed Graphs. arXiv:1710.09471Google Scholar
- James Atwood and Don Towsley. 2016. Diffusion-convolutional Neural Networks. In Proceedings of the 30th International Conference on Neural Information Processing Systems(NIPS’16). Curran Associates Inc., USA, 2001–2009. http://dl.acm.org/citation.cfm?id=3157096.3157320Google ScholarDigital Library
- Stephen W. Bailey, Dave Otte, Paul Dilorenzo, and James F. O’Brien. 2018. Fast and Deep Deformation Approximations. ACM Trans. Graph. 37, 4, Article 119 (July 2018), 12 pages. https://doi.org/10.1145/3197517.3201300Google ScholarDigital Library
- Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2013. Spectral Networks and Locally Connected Networks on Graphs. arXiv:1312.6203Google Scholar
- Dan Casas and Miguel A. Otaduy. 2018. Learning Nonlinear Soft-Tissue Dynamics for Interactive Avatars. Proc. ACM Comput. Graph. Interact. Tech. 1, 1, Article Article 10 (July 2018), 15 pages. https://doi.org/10.1145/3203187Google ScholarDigital Library
- Olivier Dionne and Martin de Lasa. 2013. Geodesic Voxel Binding for Production Character Meshes. In Proceedings of the 12th ACM SIGGRAPH/Eurographics Symposium on Computer Animation(SCA ’13). ACM Press, New York, NY, USA, 173–180. https://doi.org/10.1145/2485895.2485919Google ScholarDigital Library
- Hongyang Gao, Zhengyang Wang, and Shuiwang Ji. 2018. Large-Scale Learnable Graph Convolutional Networks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM Press, New York, NY, USA, 1416–1424. https://doi.org/10.1145/3219819.3219947Google ScholarDigital Library
- Fabian Hahn, Sebastian Martin, Bernhard Thomaszewski, Robert Sumner, Stelian Coros, and Markus Gross. 2012. Rig-space Physics. ACM Trans. Graph. 31, 4, Article 72 (July 2012), 8 pages. https://doi.org/10.1145/2185520.2185568Google ScholarDigital Library
- David K. Hammond, Pierre Vandergheynst, and Rémi Gribonval. 2011. Wavelets on graphs via spectral graph theory. Applied and Computational Harmonic Analysis 30, 2 (March 2011), 129–150. https://doi.org/10.1016/j.acha.2010.04.005Google ScholarCross Ref
- Mikael Henaff, Joan Bruna, and Yann LeCun. 2015. Deep Convolutional Networks on Graph-Structured Data. arXiv:1506.05163Google Scholar
- Ladislav Kavan, Steven Collins, Jiří Žára, and Carol O’Sullivan. 2007. Skinning with Dual Quaternions. In Proceedings of the 2007 Symposium on Interactive 3D Graphics and Games(I3D ’07). ACM Press, New York, NY, USA, 39–46. https://doi.org/10.1145/1230100.1230107Google ScholarDigital Library
- Tsuneya Kurihara and Natsuki Miyata. 2004. Modeling Deformable Human Hands from Medical Images. In Proceedings of the 2004 ACM SIGGRAPH/Eurographics Symposium on Computer Animation(SCA ’04). Eurographics Association, Goslar, DEU, 355–363. https://doi.org/10.1145/1028523.1028571Google ScholarDigital Library
- Binh Huy Le and Zhigang Deng. 2014. Robust and Accurate Skeletal Rigging from Mesh Sequences. ACM Trans. Graph. 33, 4, Article 84 (July 2014), 10 pages. https://doi.org/10.1145/2601097.2601161Google ScholarDigital Library
- J. P. Lewis, Matt Cordner, and Nickson Fong. 2000. Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-driven Deformation. In Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH ’00). ACM Press/Addison-Wesley Publishing Co., New York, NY, USA, 165–172. https://doi.org/10.1145/344779.344862Google ScholarDigital Library
- Guohao Li, Matthias Müller, Ali K. Thabet, and Bernard Ghanem. 2017. Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Washington, DC, USA, 2261–2269. https://doi.org/10.1109/CVPR.2017.243Google Scholar
- Guohao Li, Matthias Müller, Ali K. Thabet, and Bernard Ghanem. 2019. Can GCNs Go as Deep as CNNs?(2019). arXiv:1904.03751Google Scholar
- Ruoyu Li, Sheng Wang, Feiyun Zhu, and Junzhou Huang. 2018. Adaptive Graph Convolutional Neural Networks. In Proc. 32nd AAAI Conference on Artificial Intelligence. AAAI Press, Palo Alto, CA, 3546–3553.Google ScholarCross Ref
- Lijuan Liu, Youyi Zheng, Di Tang, Yi Yuan, Changjie Fan, and Kun Zhou. 2019. NeuroSkinning: Automatic Skin Binding for Production Characters with Deep Graph Networks. ACM Trans. Graph. 38, 4, Article 114 (July 2019), 12 pages. https://doi.org/10.1145/3306346.3322969Google ScholarDigital Library
- Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J. Black. 2015. SMPL: A Skinned Multi-Person Linear Model. ACM Trans. Graph. 34, 6, Article Article 248 (Oct. 2015), 16 pages. https://doi.org/10.1145/2816795.2818013Google ScholarDigital Library
- Ran Luo, Tianjia Shao, Huamin Wang, Weiwei Xu, Xiang Chen, Kun Zhou, and Yin Yang. 2018. NNWarp: Neural Network-Based Nonlinear Deformation. IEEE Transactions on Visualization and Computer Graphics (2018), 14. https://doi.org/10.1109/TVCG.2018.2881451Early Access.Google Scholar
- Nadia Magnenat-Thalmann, Richard Laperrière, and Daniel Thalmann. 1988. Joint-dependent Local Deformations for Hand Animation and Object Grasping. In Proceedings on Graphics Interface ’88. Canadian Information Processing Society, Toronto, Ont., Canada, 26–33. http://dl.acm.org/citation.cfm?id=102313.102317Google ScholarDigital Library
- Aleka McAdams, Yongning Zhu, Andrew Selle, Mark Empey, Rasmus Tamstorf, Joseph Teran, and Eftychios Sifakis. 2011. Efficient Elasticity for Character Skinning with Contact and Collisions. ACM Trans. Graph. 30, 4, Article 37 (July 2011), 12 pages. https://doi.org/10.1145/2010324.1964932Google ScholarDigital Library
- Federico Monti, Davide Boscaini, Jonathan Masci, Emanuele Rodola, Jan Svoboda, and Michael M. Bronstein. 2017. Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Washington, DC, USA, 5115–5124. https://doi.org/10.1109/CVPR.2017.576Google Scholar
- Junjun Pan, Lijuan Chen, Yuhan Yang, and Hong Qin. 2018. Automatic Skinning and Weight Retargeting of Articulated Characters Using Extended Position-Based Dynamics. The Visual Computer 34, 10 (2018), 1285–1297.Google ScholarDigital Library
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Proceedings of the 31st International Conference on Neural Information Processing Systems(NIPS’17). Curran Associates Inc., USA, 5998–6008.Google ScholarDigital Library
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph Attention Networks. arXiv:1710.10903Google Scholar
- Hongyi Xu and Jernej Barbič. 2016. Pose-space Subspace Dynamics. ACM Trans. Graph. 35, 4, Article 35 (July 2016), 14 pages. https://doi.org/10.1145/2897824.2925916Google ScholarDigital Library
- Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2018. Graph Neural Networks: A Review of Methods and Applications. arXiv:1812.08434Google Scholar
Recommendations
As-rigid-as-possible mesh deformation and its application in hexahedral mesh generation
This paper presents an efficient and stable as-rigid-as-possible mesh deformation algorithm for planar shape deformation and hexahedral mesh generation. The deformation algorithm aims to preserve two local geometric properties: scale-invariant intrinsic ...
Attachment-based character deformation
SCA '17: Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer AnimationWhile advancements have made it easier to work with digital characters, it remains difficult to author animations that display the free and highly expressive shape change that characterize hand-drawn animation. We present a deformation method that ...
Improving Chinese Character Representation with Formation Graph Attention Network
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementChinese characters are often composed of subcharacter components which are also semantically informative, and the component-level internal semantic features of a Chinese character inherently bring with additional information that benefits the semantic ...
Comments