imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose
This provides a holistic generative model for 3D human bodies, enabling applications like animation and virtual reality, but it is incremental as it builds on prior implicit and mesh-based methods.
The authors tackled the problem of creating a generative model for 3D human shape and articulated pose by introducing imGHUM, which uses a signed distance function without an explicit template mesh, achieving accuracy on par with state-of-the-art mesh-based models.
We present imGHUM, the first holistic generative model of 3D human shape and articulated pose, represented as a signed distance function. In contrast to prior work, we model the full human body implicitly as a function zero-level-set and without the use of an explicit template mesh. We propose a novel network architecture and a learning paradigm, which make it possible to learn a detailed implicit generative model of human pose, shape, and semantics, on par with state-of-the-art mesh-based models. Our model features desired detail for human models, such as articulated pose including hand motion and facial expressions, a broad spectrum of shape variations, and can be queried at arbitrary resolutions and spatial locations. Additionally, our model has attached spatial semantics making it straightforward to establish correspondences between different shape instances, thus enabling applications that are difficult to tackle using classical implicit representations. In extensive experiments, we demonstrate the model accuracy and its applicability to current research problems.