Research on 2D Animation Simulation Based on Artificial Intelligence and Biomechanical Modeling

Fangming Dai; Zhiyong Li

doi:10.4108/eetpht.10.5907

Authors

Fangming Dai ShenZhen Polytechnic University
Zhiyong Li ShenZhen Polytechnic University

DOI:

https://doi.org/10.4108/eetpht.10.5907

Keywords:

biomechanical modelling, artificial intelligence, character animation, deep neural network

Abstract

Animation techniques have been completely transformed by the union of Artificial Intelligence (AI) and biomechanical modeling, particularly in 2D animation. This study looks at a combination of AI and biomechanics to address the challenges of simulating 2D animation. Current approaches in 2D animation often struggle to achieve lifelike and fluid movements, especially when representing complex motion or interaction. These traditional techniques rely on manual keyframing or physics simulation, which may be time-consuming and do not provide the rich detail needed for realism in animations. To meet these aspects, this study suggested 2D animation using Artificial Intelligence with Biomechanical Modeling (2D-AI-BM). Our approach thus harnesses Deep Neural Network (DNN) for moving forecasts and improvement using biopsychological principles to help us imitate natural human actions better. In addition to character animation, it could apply to interactive storytelling and educational simulations. As a result, animators get more control over motion generation while drastically reducing the necessity for manual intervention through this fusion of AI and biomechanics, which smoothens the production pipeline for animations. This paper considers several important metrics to evaluate the proposed approach’s effectiveness, including user satisfaction, computational efficiency, motion smoothness and realism. Comparative studies with classical animation methods showed that the method generates realistic movements on 2D characters while saving time during production. The numerical findings exemplify that the recommended 2D-AI-BM model improves an accuracy rate of 97.4%, computational efficiency ratio of 96.3%, motion control ratio of 95.4%, pose detection ratio of 94.8% and scalability ratio of 93.2% compared to other popular techniques.

Downloads

Download data is not yet available.

References

Farahani, J., Soltani, P., & Roberts, R. E. (2020). Expertise differences in a 2D animation simulation decision-making task: The influence of presentation speed on performance. Progress in brain research, 253, 87-100. DOI: https://doi.org/10.1016/bs.pbr.2020.06.017

Schreck, C., & Wojtan, C. (2022, May). Coupling 3D liquid simulation with 2D wave propagation for large scale water surface animation using the equivalent sources method. In Computer Graphics Forum (Vol. 41, No. 2, pp. 343-353). DOI: https://doi.org/10.1111/cgf.14478

Untari, R., Kamdi, W., Dardiri, A., Hadi, S., & Nurhadi, D. (2020). The development and application of interactive multimedia in project-based learning to enhance students' achievement for 2D animation making. International Journal of Emerging Technologies in Learning (IJET), 15(16), 17-30. DOI: https://doi.org/10.3991/ijet.v15i16.16521

Morgenroth, D., Reinhardt, S., Weiskopf, D., & Eberhardt, B. (2020, December). Efficient 2D simulation on moving 3D surfaces. In Computer Graphics Forum (Vol. 39, No. 8, pp. 27-38). DOI: https://doi.org/10.1111/cgf.14098

Ejimonye, J. C., Ugwuanyi, C. S., Okeke, C. I. O., & Nwoye, M. N. (2020). Two-dimensional animation and students’ achievement in mathematical economics: implications for science teaching. International Journal of Engineering Research and Technology, 13(6), 1220-1230. DOI: https://doi.org/10.37624/IJERT/13.6.2020.1220-1230

Farahani, J., Soltani, P., Rezlescu, C., & Walsh, V. (2020). Assessing decision making using 2D animations in elite academy footballers. Progress in Brain Research, 253, 71-85. DOI: https://doi.org/10.1016/bs.pbr.2020.06.016

Verma, M., Thapliyal, V., Mishra, A., & Rani, S. (2024). Efficacy of 3D Monte Carlo Simulations vis-à-vis 2D in the Estimation of Pi: A Multifaceted Approach. International Journal of Applied and Computational Mathematics, 10(2), 1-15. DOI: https://doi.org/10.1007/s40819-024-01708-6

Even, M., Bénard, P., & Barla, P. (2023, May). Non‐linear Rough 2D Animation using Transient Embeddings. In Computer Graphics Forum (Vol. 42, No. 2, pp. 411-425). DOI: https://doi.org/10.1111/cgf.14771

Alherz, A., Tsuruta, N., & Kondo, K. (2020). Multiple-character animation systems for children at different educational stages. International Journal of Asia Digital Art and Design Association, 24(1), 1-7.

Wang, J., & Gao, J. (2023). Research on 3D Animation Technology of Human and Scene Based on Virtual Reality. Art and Performance Letters, 4(1), 12-17.

Bishop, P. J., Cuff, A. R., & Hutchinson, J. R. (2021). How to build a dinosaur: Musculoskeletal modeling and simulation of locomotor biomechanics in extinct animals. Paleobiology, 47(1), 1-38. DOI: https://doi.org/10.1017/pab.2020.46

Feldotto, B., Morin, F. O., & Knoll, A. (2022). The neurorobotics platform robot designer: modeling morphologies for embodied learning experiments. Frontiers in Neurorobotics, 16, 856727. DOI: https://doi.org/10.3389/fnbot.2022.856727

Ling, X., Zhu, Y., Liu, W., Liang, J., & Yang, J. (2023). The Generation of Articulatory Animations Based on Keypoint Detection and Motion Transfer Combined with Image Style Transfer. Computers, 12(8), 150. DOI: https://doi.org/10.3390/computers12080150

Li, J., & Wang, J. (2023). Digital animation multimedia information synthesis based on mixed reality framework with specialized analysis on speech data. International journal of speech technology, 26(1), 63-76. DOI: https://doi.org/10.1007/s10772-021-09940-x

Babadi, A., Van de Panne, M., Liu, C. K., & Hämäläinen, P. (2021). Learning Task-Agnostic Action Spaces for Movement Optimization. IEEE Transactions on Visualization and Computer Graphics, 28(12), 4700-4712. DOI: https://doi.org/10.1109/TVCG.2021.3100095

Liu, Y., Zheng, C., Xu, F., Tong, X., & Guo, B. (2020). Data-driven 3d neck modeling and animation. IEEE Transactions on Visualization and Computer Graphics, 27(7), 3226-3237. DOI: https://doi.org/10.1109/TVCG.2020.2967036

Wu, Y., Chen, Z., Liu, S., Ren, Z., & Wang, S. (2022). Casa: Category-agnostic skeletal animal reconstruction. Advances in Neural Information Processing Systems, 35, 28559-28574.

Ayas, A. Y., Aydin, H., Çetinkaya, A., & Güney, Z. (2023). Artificial Intelligence (AI)-Based Self-Deciding Character Development Application in Two-Dimensional Video Games. Bilgi ve İletişim Teknolojileri Dergisi, 5(1), 1-19. DOI: https://doi.org/10.53694/bited.1247338

Liu, K., Chang, K. M., Liu, Y. J., & Chen, J. H. (2020). Animated Character Style Investigation with Decision Tree Classification. Symmetry, 12(8), 1261. DOI: https://doi.org/10.3390/sym12081261

Kumar, A., Jilani Saudagar, A. K., AlKhathami, M., Alsamani, B., Abul Hasanat, M. H., Khan, M. B., ... & Singh, K. U. (2022). AIAVRT: 5.0 Transformation in Medical Education with Next Generation AI-3D Animation and VR Integrated Computer Graphics Imagery. Traitement du Signal, 39(5). DOI: https://doi.org/10.18280/ts.390542

Ding, W., & Li, W. (2023). High speed and accuracy of animation 3D pose recognition based on an improved deep convolution neural network. Applied Sciences, 13(13), 7566. DOI: https://doi.org/10.3390/app13137566

Fangbemi, A. S., Lu, Y. F., Xu, M. Y., Luo, X. W., Rolland, A., & Raissi, C. (2020). ZooBuilder: 2D and 3D pose estimation for quadrupeds using synthetic data. arXiv preprint arXiv:2009.05389.

Wan, Y., Edmond, M. A., Kitz, C., Southern, J., & Holman, H. A. (2023). An integrated workflow for 2D and 3D posture analysis during vestibular system testing in mice. Frontiers in Neurology, 14, 1281790. DOI: https://doi.org/10.3389/fneur.2023.1281790

Kumar, A., Saudagar, A. K. J., Alkhathami, M., Alsamani, B., Khan, M. B., Hasanat, M. H. A., ... & Srinivasan, B. (2023). Gamified learning and assessment using ARCS with next-generation AIoMT integrated 3D animation and virtual reality simulation. Electronics, 12(4), 835. DOI: https://doi.org/10.3390/electronics12040835

Siyao, L., Li, Y., Li, B., Dong, C., Liu, Z., & Loy, C. C. (2022). Animerun: 2d animation visual correspondence from open source 3d movies. Advances in Neural Information Processing Systems, 35, 18996-19007.

Mundt, M., Oberlack, H., Morris, C., Funken, J., Potthast, W., & Alderson, J. (2021). No dataset too small! Animating 3D motion data to enlarge 2D video databases. ISBS Proceedings Archive, 39(1), 25.

Asraf, S. M. H., Abdullasim, N., & Romli, R. (2020, February). Hybrid animation: implementation of motion capture. In IOP Conference Series: Materials Science and Engineering (Vol. 767, No. 1, p. 012065). IOP Publishing. DOI: https://doi.org/10.1088/1757-899X/767/1/012065

https://www.kaggle.com/datasets/dbdmobile/myanimelist-dataset