Character Design For 3d Animation

• Published: 18 April 2019

Research on 3D animation character design based on multimedia interaction

Multimedia Tools and Applications (2019)Cite this article

Abstract

Aiming at the low intelligence, low interaction performance and low efficiency of traditional 3D animation characters in multimedia interaction, this paper designs a multimedia scene model and a 3D animation role agent based on the multimedia interaction model of Computer Supported Cooperative work, and designs a multimedia scene model and a 3D animation role agent through 3DS Max. In order to make Agent more intelligent in multimedia interaction, a deep Q-Learning neural network model is introduced in this paper. Through this model, the reinforcement learning of 3D animation role agent in multimedia interaction scenarios is introduced. Taking basketball games as an example, multimedia interactive scenes and 3D animation role agent are constructed by using 3DS Max software. In the subsequent comparative experiments, it is proved that the deep Q-Learning neural network model constructed in this paper is more suitable for 3D animation role agent in multimedia interactive environment. It makes 3D animation characters more suitable for multimedia interaction, and builds higher performance and efficiency of intelligent interactive action.

Access options

Buy single article

Instant access to the full article PDF.

34,95 €

Price includes VAT (Indonesia)
Tax calculation will be finalised during checkout.

References

1. 1.

   Bessmeltsev M, Chang W, Vining N et al (2015) Modeling character canvases from cartoon drawings[J]. ACM Transactions on Graphics (TOG) 34(5):162

   Article  Google Scholar

2. 2.

   Caicedo JC, Lazebnik S (2015) Active object localization with deep reinforcement learning[C]//Proceedings of the IEEE International Conference on Computer Vision. 2488–2496

3. 3.

   Darlington J (2018) Techno-Wizardry and movie magic: the trace of labour (or lack thereof) in 3D digital animation[J]. Information, Communication & Society, 1–17

4. 4.

   Duan Y, Chen X, Houthooft R, et al. (2016) Benchmarking deep reinforcement learning for continuous control[C]//International Conference on Machine Learning. 1329–1338

5. 5.

   Gao Q, Gu H, Zhao P et al (2018) Fabrication of electrospun nanofibrous scaffolds with 3D controllable geometric shapes[J]. Mater Des 157:159–169

   Article  Google Scholar

6. 6.

   Gunanto SG, Hariadi M, Yuniarno EM (2016) Generating weight paint area on 3D cartoon-face models[J]. International Information Institute (Tokyo). Information 19(9B):4183

   Google Scholar

7. 7.

   Gunanto SG, Hariadi M, Yuniarto EM (2016) Improved 3D face feature-point nearest neighbor clustering using orthogonal face map[J]. Adv Sci Lett 22(8):1882–1886

   Article  Google Scholar

8. 8.

   Kulkarni TD, Narasimhan K, Saeedi A, et al. (2016) Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation[C]//Advances in neural information processing systems. 3675–3683

9. 9.

   Liu Y, Wang W. (2016) Body-structure-based cartoon character modeling from multi-view hand-drawings[C]//Computer Science and Network Technology (ICCSNT), 2016 5th International Conference on. IEEE, 89–93

10. 10.

    Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning[J]. Nature 518(7540):529

    Article  Google Scholar

11. 11.

    Mnih V, Badia A P, Mirza M, et al. (2016) Asynchronous methods for deep reinforcement learning[C]//International conference on machine learning. 1928–1937

12. 12.

    Plattner N, Noé F (2015) Protein conformational plasticity and complex ligand-binding kinetics explored by atomistic simulations and Markov models[J]. Nat Commun 6:7653

    Article  Google Scholar

13. 13.

    Van Hasselt H, Guez A, Silver D (2016) Deep Reinforcement Learning with Double Q-Learning[C]//AAAI 2:5

    Google Scholar

14. 14.

    Xie C, Zhang Z, Wang C et al (2018) Object tracking method based on 3D cartoon animation in broadcast soccer videos[J]. International Journal of Performability Engineering 14(8):1774

    Google Scholar

15. 15.

    Zhou J, Wu HT, Liu Z, et al. (2018) 3D cartoon face rigging from sparse examples[J]. The Visual Computer, 1–11

16. 16.

    Zhu Y, Mottaghi R, Kolve E, et al. (2017) Target-driven visual navigation in indoor scenes using deep reinforcement learning[C]//Robotics and Automation (ICRA), 2017 IEEE International Conference on. IEEE, 3357–3364

Download references

Author information

Affiliations

1. South China Institute of Software Engineering.GU, Guangzhou, 510900, Guangdong, China

   Ping Hu

2. GuangZhou City Construction College, Guangzhou, 510900, Guangdong, China

   Jian Wen

Corresponding author

Correspondence to Ping Hu.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

About this article

Cite this article

Hu, P., Wen, J. Research on 3D animation character design based on multimedia interaction. Multimed Tools Appl (2019). https://doi.org/10.1007/s11042-019-7538-z

Download citation

• Received: 28 December 2018

• Revised: 27 February 2019

• Accepted: 20 March 2019

• Published: 18 April 2019

• DOI : https://doi.org/10.1007/s11042-019-7538-z

Keywords

• Multimedia interaction
• Collaborative work
• 3D animation characters
• Deep Q-learning neural network

Character Design For 3d Animation

Source: https://link.springer.com/article/10.1007/s11042-019-7538-z

Posted by: thompsonfacticked.blogspot.com

Share this post