Semi-Supervised Learning of Physics-Enforced Garment Prediction

We propose a novel learning framework for garment draping prediction that can incorporate arbitrary loss functions at runtime. Previous methods do not address several inconsistencies arising from the enforcement of physical constraints, such as wrinkle dynamics, (heterogeneous) material properties, the (in)ability to fit a wide range of body shapes, etc. To address these problems, we propose a semi-supervised learning framework composed of three key components. First, a physics-inspired supervision on a novel neural network that captures multi-scale features dynamically. Second, an unsupervised process coupled to the physics of garments at runtime. Finally, self-correction of the network based on the optimized samples in the previous stage. Experiments show that our method can reproduce wrinkles and folds more accurately than prior work across a wide spectrum of body shapes, incorporate fabric material properties and other design elements during inference time, while considerably reducing the amount of training data.