Building Statistical Shape Spaces for 3D Human Modeling
This work addresses the problem of insufficiently varied 3D human models for vision and graphics applications, though it is incremental as it builds on existing statistical representations.
The authors tackled the limited expressiveness of existing 3D human shape models by rebuilding a statistical body representation using the largest commercially available scan database, resulting in a publicly available model that shows improved accuracy and generality, with enhanced performance for human body reconstruction from sparse input data.
Statistical models of 3D human shape and pose learned from scan databases have developed into valuable tools to solve a variety of vision and graphics problems. Unfortunately, most publicly available models are of limited expressiveness as they were learned on very small databases that hardly reflect the true variety in human body shapes. In this paper, we contribute by rebuilding a widely used statistical body representation from the largest commercially available scan database, and making the resulting model available to the community (visit http://humanshape.mpi-inf.mpg.de). As preprocessing several thousand scans for learning the model is a challenge in itself, we contribute by developing robust best practice solutions for scan alignment that quantitatively lead to the best learned models. We make implementations of these preprocessing steps also publicly available. We extensively evaluate the improved accuracy and generality of our new model, and show its improved performance for human body reconstruction from sparse input data.