ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

BiHMP-GAN: Bidirectional 3D human motion prediction GAN

Kundu, JN and Gor, M and Venkatesh Babu, R (2019) BiHMP-GAN: Bidirectional 3D human motion prediction GAN. In: 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019, 27 January - 1 February 2019, Honolulu, pp. 8553-8560.

[img] PDF
33_aaa_con_art_int_8553-8560_2019.pdf - Published Version
Restricted to Registered users only

Download (1MB)
Official URL: https://doi.org/10.1609/aaai.v33i01.33018553


Human motion prediction model has applications in various fields of computer vision. Without taking into account the inherent stochasticity in the prediction of future pose dynamics, such methods often converges to a deterministic undesired mean of multiple probable outcomes. Devoid of this, we propose a novel probabilistic generative approach called Bidirectional Human motion prediction GAN, or BiHMP-GAN. To be able to generate multiple probable human-pose sequences, conditioned on a given starting sequence, we introduce a random extrinsic factor r, drawn from a predefined prior distribution. Furthermore, to enforce a direct content loss on the predicted motion sequence and also to avoid mode-collapse, a novel bidirectional framework is incorporated by modifying the usual discriminator architecture. The discriminator is trained also to regress this extrinsic factor r, which is used alongside with the intrinsic factor (encoded starting pose sequence) to generate a particular pose sequence. To further regularize the training, we introduce a novel recursive prediction strategy. In spite of being in a probabilistic framework, the enhanced discriminator architecture allows predictions of an intermediate part of pose sequence to be used as a conditioning for prediction of the latter part of the sequence. The bidirectional setup also provides a new direction to evaluate the prediction quality against a given test sequence. For a fair assessment of BiHMP-GAN, we report performance of the generated motion sequence using (i) a critic model trained to discriminate between real and fake motion sequence, and (ii) an action classifier trained on real human motion dynamics. Outcomes of both qualitative and quantitative evaluations, on the probabilistic generations of the model, demonstrate the superiority of BiHMP-GAN over previously available methods.

Item Type: Conference Paper
Publication: 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
Publisher: AAAI Press
Additional Information: The copyright for this article belongs to AAAI Press.
Keywords: Artificial intelligence; Forecasting; Predictive analytics; Quality control, Extrinsic factors; Intermediate parts; Intrinsic factors; Prediction quality; Prior distribution; Probabilistic framework; Quantitative evaluation; Recursive prediction, Motion estimation
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited: 02 Dec 2022 06:13
Last Modified: 02 Dec 2022 06:13
URI: https://eprints.iisc.ac.in/id/eprint/78135

Actions (login required)

View Item View Item