Garment Recovery with Shape and Deformation Priors
This addresses the problem of realistic garment modeling for applications such as animation and simulation, though it appears incremental as it builds on prior work in clothing modeling.
The paper tackles the challenge of modeling loose-fitting clothing from real-world images by introducing a fitting approach that uses shape and deformation priors learned from synthetic data, resulting in accurate garment geometry recovery that can be directly used in applications like animation and simulation.
While modeling people wearing tight-fitting clothing has made great strides in recent years, loose-fitting clothing remains a challenge. We propose a method that delivers realistic garment models from real-world images, regardless of garment shape or deformation. To this end, we introduce a fitting approach that utilizes shape and deformation priors learned from synthetic data to accurately capture garment shapes and deformations, including large ones. Not only does our approach recover the garment geometry accurately, it also yields models that can be directly used by downstream applications such as animation and simulation.