Learn to Walk Across Ages: Motion Augmented Multi-Age Group Gait Video Translation

Abstract

We propose a framework for multi-age group gait video translation in which, for the first time, individuality-preserving aging patterns in walking style are learnt. More specifically, we build our framework on an existing multi-domain image translation model. Because the existing multi-domain image translation model was originally designed for a still image, we extend it to gait video by introducing a motion-augmented network architecture with three streams, where gait period, period-normalized phase-synchronized gait video, and its frame difference sequence are each input to one stream. We then train the network to ensure three aspects: aging effect (using an age group classification loss), individuality preservation (using a reconstruction loss), and gait realism (using an adversarial loss). Our framework quantitatively and qualitatively outperforms state-of-the-art age progression/regression methods on the largest gait database, OULP-Age, with respect to both age group classification and identity recognition.

Keywords

• Gait aging
• gait video generation