Body shape diversity in the training data and consequences on motion generation

Describing human movement is key to many applications, ranging from medicine to 3D animation. Morphology is an important factor influencing how people move, but as of yet it is seldom accounted for in human-centric tasks like motion generation. In this study, we first assess the diversity of body shapes in real human motion datasets, then demonstrate the benefits of morphology-aware motion generation. We reveal biases in the data regarding body shape, in particular for body fat and gender representation. Considering the incompleteness of even the largest motion-capture datasets, proving quantitatively that morphology influences motion is difficult using existing tools: we thus propose a new metric relying on 3D body mesh self-collision, and use it to demonstrate that individuals with varied body mass indices also differ in their movements. One consequence is that generic, morphology-agnostic generated poses tend to be unsuitable for the body models they are used with, and we show that it tends to increase self-collision artifacts. Building upon these results, we show that morphology-aware motion generation reduces mesh self-collision artifacts despite not being trained for it explicitly, even when using a common backbone and a naive conditioning strategy. Morphology-aware generation can also be seamlessly integrated to most pose and motion generation architectures with little-to-no extra computational cost and without compromising generation diversity of realism. • Morphology (for instance body fat) has an influence on how people move. • Public motion capture datasets do not contain enough participants with high body fat. • Women make up 40% of motion capture subjects but have only 32% of the screen time. • A lack of body shape diversity in the data negatively impacts machine learning models. • Accounting for morphology during motion generation for 3D animation improves realism.