TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model
This work addresses the problem of localized shape control in human shape modeling for tasks like shape and pose inference, though it is incremental as it builds on existing volumetric and anatomical approaches.
The paper tackles the limited localized shape control in existing human shape models by learning an anatomically constrained volumetric model using self-supervised learning on an enlarged dataset, resulting in a model that enables shape sampling, localized manipulation, and fast inference from surface scans.
Human shape spaces have been extensively studied, as they are a core element of human shape and pose inference tasks. Classic methods for creating a human shape model register a surface template mesh to a database of 3D scans and use dimensionality reduction techniques, such as Principal Component Analysis, to learn a compact representation. While these shape models enable global shape modifications by correlating anthropometric measurements with the learned subspace, they only provide limited localized shape control. We instead register a volumetric anatomical template, consisting of skeleton bones and soft tissue, to the surface scans of the CAESAR database. We further enlarge our training data to the full Cartesian product of all skeletons and all soft tissues using physically plausible volumetric deformation transfer. This data is then used to learn an anatomically constrained volumetric human shape model in a self-supervised fashion. The resulting TailorMe model enables shape sampling, localized shape manipulation, and fast inference from given surface scans.