Motion Capture Synthesis with Adversarial Learning

Qi Wang (1, 2) , Thierry Artières (1, 2)

1 LIF - Laboratoire d'informatique Fondamentale de Marseille
2 QARMA - éQuipe AppRentissage et MultimediA [Marseille]

We propose a new statistical modeling approach that we call Sequential Adversarial Auto-encoder (SAAE) for learning a synthesis model for motion sequences. This model exploits the adversarial idea that has been popularized in the machine learning field for learning accurate generative models. We further propose a conditional variant of this model that takes as input an additional information such as the activity which is performed in a sequence, or the emotion with which it is performed, and which allows to perform synthesis in context.

Mots clés: Sequence Synthesis; Avatar Animation

Domaines: Réseau de neurones [cs.NE]; Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]

Qi Wang, Thierry Artières. Motion Capture Synthesis with Adversarial Learning. Intelligent Virtual Agents, Aug 2017, Stockholm, Sweden. ⟨hal-01691463⟩