AnthroNet: Conditional Generation of Humans via Anthropometrics
This work addresses the need for realistic human generation in computer vision and graphics, offering a tool for non-commercial academic research with millions of unique identities, though it is incremental in using synthetic data.
The paper tackles the problem of generating diverse human body shapes and poses by introducing a novel human body model trained end-to-end on synthetic data, achieving highly accurate mesh representations and precise anthropometry from 100k procedurally-generated meshes.
We present a novel human body model formulated by an extensive set of anthropocentric measurements, which is capable of generating a wide range of human body shapes and poses. The proposed model enables direct modeling of specific human identities through a deep generative architecture, which can produce humans in any arbitrary pose. It is the first of its kind to have been trained end-to-end using only synthetically generated data, which not only provides highly accurate human mesh representations but also allows for precise anthropometry of the body. Moreover, using a highly diverse animation library, we articulated our synthetic humans' body and hands to maximize the diversity of the learnable priors for model training. Our model was trained on a dataset of $100k$ procedurally-generated posed human meshes and their corresponding anthropometric measurements. Our synthetic data generator can be used to generate millions of unique human identities and poses for non-commercial academic research purposes.