Abstract
Motion capture data has been largely needed in the movie and game industry in recent years. Since the motion capture system is expensive and requires manual post-processing, motion synthesis is a plausible solution to acquire more motion data. However, generating the action-conditioned, realistic, and diverse 3D human motions given the semantic action labels is still challenging because the mapping from semantic labels to real motion sequences is hard to depict. Previous work made some positive attempts like appending label tokens to pose encoding and performing action bias on latent space. However, how to synthesize diverse motions that accurately match the given label is still not fully explored. In this paper, we propose the Uncoupled-Modulation Conditional Variational AutoEncoder (UM-CVAE) to generate action-conditioned motions from scratch in an uncoupled manner. The main idea is twofold: (i) training an action-agnostic encoder to weaken the action-related information to learn the easy-modulated latent representation; (ii) strengthening the action-conditioned process with FiLM-based action-aware modulation. We conduct extensive experiments on the HumanAct12, UESTC, and BABEL datasets, demonstrating that our method achieves state-of-the-art performance both qualitatively and quantitatively with potential applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahn, H., Ha, T., Choi, Y., Yoo, H., Oh, S.: Text2Action: generative adversarial synthesis from language to action. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 5915–5920. IEEE (2018)
Ahuja, C., Morency, L.P.: Language2Pose: natural language grounded pose forecasting. In: 2019 International Conference on 3D Vision (3DV), pp. 719–728. IEEE (2019)
Barsoum, E., Kender, J., Liu, Z.: HP-GAN: probabilistic 3D human motion prediction via GAN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1418–1427 (2018)
Brand, M., Hertzmann, A.: Style machines. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 183–192 (2000)
Cheng, X., Xu, W., Wang, T., Chu, W.: Variational semi-supervised aspect-term sentiment analysis via transformer. arXiv preprint arXiv:1810.10437 (2018)
Clavet, S.: Motion matching and the road to next-gen animation. In: Proceedings of the GDC (2016)
Corona, E., Pumarola, A., Alenya, G., Moreno-Noguer, F.: Context-aware human motion prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6992–7001 (2020)
Cui, Q., Sun, H., Yang, F.: Learning dynamic relationships for 3D human motion prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6519–6527 (2020)
Fang, L., Zeng, T., Liu, C., Bo, L., Dong, W., Chen, C.: Transformer-based conditional variational autoencoder for controllable story generation. arXiv preprint arXiv:2101.00828 (2021)
Guo, C., et al.: Action2Motion: conditioned generation of 3D human motions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2021–2029 (2020)
Holden, D., Kanoun, O., Perepichka, M., Popa, T.: Learned motion matching. ACM Trans. Graph. 39(4), 53:1–53:12 (2020)
Holden, D., Komura, T., Saito, J.: Phase-functioned neural networks for character control. ACM Trans. Graph. 36(4), 1–13 (2017)
Holden, D., Saito, J., Komura, T.: A deep learning framework for character motion synthesis and editing. ACM Trans. Graph. 35(4), 1–11 (2016)
Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5308–5317 (2016)
Ji, Y., Xu, F., Yang, Y., Shen, F., Shen, H.T., Zheng, W.S.: A large-scale RGB-D database for arbitrary-view human action recognition. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1510–1518 (2018)
Jiang, J., Xia, G.G., Carlton, D.B., Anderson, C.N., Miyakawa, R.H.: Transformer VAE: a hierarchical model for structure-aware and interpretable music representation learning. In: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 516–520. IEEE (2020)
Kundu, J.N., Gor, M., Babu, R.V.: BiHMP-GAN: bidirectional 3D human motion prediction GAN. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8553–8560 (2019)
Lee, H.Y., et al.: Dancing to music. Adv. Neural Inf. Process. Syst. 32 (2019)
Li, J., et al.: Learning to generate diverse dance motions with transformer. arXiv preprint arXiv:2008.08171 (2020)
Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST++. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 13401–13412 (2021)
Lin, X., Amer, M.R.: Human motion modeling using DVGANs. arXiv preprint arXiv:1804.10652 (2018)
Ling, H.Y., Zinno, F., Cheng, G., Van De Panne, M.: Character controllers using motion VAEs. ACM Trans. Graph. 39(4), 40:1–40:12 (2020)
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6), 1–16 (2015)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)
Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5442–5451 (2019)
Mao, W., Liu, M., Salzmann, M.: History repeats itself: human motion prediction via motion attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 474–489. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_28
Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2891–2900 (2017)
Mason, I., Starke, S., Komura, T.: Real-time style modelling of human locomotion via feature-wise transformations and local motion phases. arXiv preprint arXiv:2201.04439 (2022)
Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10985–10995 (2021)
Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., Black, M.J.: BABEL: bodies, action and behavior with English labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 722–731 (2021)
Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 36(6) (2017)
Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12026–12035 (2019)
Sofianos, T., Sampieri, A., Franco, L., Galasso, F.: Space-time-separable graph convolutional network for pose forecasting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11209–11218 (2021)
Starke, S., Zhang, H., Komura, T., Saito, J.: Neural state machine for character-scene interactions. ACM Trans. Graph. 38(6), 178:1–178:14 (2019)
Starke, S., Zhao, Y., Komura, T., Zaman, K.: Local motion phases for learning multi-contact character movements. ACM Trans. Graph. 39(4), 54:1–54:13 (2020)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6924–6932 (2017)
Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: video forecasting by generating pose futures. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3332–3341 (2017)
Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 283–298 (2007)
Wang, Z., Chai, J., Xia, S.: Combining recurrent neural networks and adversarial training for human motion synthesis and control. IEEE Trans. Visual Comput. Graphics 27(1), 14–28 (2019)
Xia, S., Wang, C., Chai, J., Hodgins, J.: Realtime style transfer for unlabeled heterogeneous human motion. ACM Trans. Graph. 34(4), 1–10 (2015)
Yuan, Y., Kitani, K.: DLow: diversifying latent flows for diverse human motion prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 346–364. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_20
Zhang, H., Starke, S., Komura, T., Saito, J.: Mode-adaptive neural networks for quadruped motion control. ACM Trans. Graph. 37(4), 1–11 (2018)
Zhong, C., Hu, L., Xia, S.: Spatial–temporal modeling for prediction of stylized human motion. Neurocomputing 511, 34–42 (2022)
Zhong, C., Hu, L., Zhang, Z., Ye, Y., Xia, S.: Spatio-temporal gating-adjacency GCN for human motion prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6447–6456 (2022)
Zou, S., et al.: 3D human shape reconstruction from a polarization image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 351–368. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_21
Acknowledgement
This work was supported by the National Key R &D Program of Science and Technology for Winter Olympics (No. 2020YFF0304701) and the National Natural Science Foundation of China (No. 61772499).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhong, C., Hu, L., Zhang, Z., Xia, S. (2022). Learning Uncoupled-Modulation CVAE for 3D Action-Conditioned Human Motion Synthesis. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13681. Springer, Cham. https://doi.org/10.1007/978-3-031-19803-8_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-19803-8_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19802-1
Online ISBN: 978-3-031-19803-8
eBook Packages: Computer ScienceComputer Science (R0)