SPHEAR: Spherical Head Registration for Complete Statistical 3D Modeling
This provides a tool for realistic visual data generation and reconstruction in computer vision and graphics, though it appears incremental by building on existing statistical modeling with a novel registration method.
The paper tackles the problem of creating a parametric 3D human head model by introducing SPHEAR, which uses spherical embeddings for registration to improve reconstruction fidelity and reduce human intervention, resulting in a complete model that generates diverse head attributes like shapes, expressions, and hair strands with high accuracy and efficiency.
We present \emph{SPHEAR}, an accurate, differentiable parametric statistical 3D human head model, enabled by a novel 3D registration method based on spherical embeddings. We shift the paradigm away from the classical Non-Rigid Registration methods, which operate under various surface priors, increasing reconstruction fidelity and minimizing required human intervention. Additionally, SPHEAR is a \emph{complete} model that allows not only to sample diverse synthetic head shapes and facial expressions, but also gaze directions, high-resolution color textures, surface normal maps, and hair cuts represented in detail, as strands. SPHEAR can be used for automatic realistic visual data generation, semantic annotation, and general reconstruction tasks. Compared to state-of-the-art approaches, our components are fast and memory efficient, and experiments support the validity of our design choices and the accuracy of registration, reconstruction and generation techniques.