A data-driven approach for real-time clothes simulation

A data-driven approach for the real-time processing of clothes, particularly suitable for simulating dresses worn by virtual characters, is proposed. It starts, prior to real-time simulation, by analyzing cloth behavior in relation to the underlying skeleton movement from a presimulated sequence of the cloth obtained using any high-quality off-line simulators. The idea is to use this analysis to find an optimal combination of physics-based simulation and geometric approximation of the simulator; potentially colliding regions are defined on the cloth such that they will hold true for the skeleton movement that closely matches that of presimulated sequence. At runtime, using these analyses, our simulation process provides both visually pleasing results and performance, as long as the motion of the character remains sufficiently close to the original sequence used for the precomputation. The key contributions of this paper are (1) efficient collision handling that prunes out potentially colliding objects by using the off-line simulation sequence as examples; (2) data-driven fix-up process for the coarse mesh simulation that deduces the gross behavior of the cloth; and (3) geometric approximation of the fine mesh deformation, responsible for details in the shape of the cloth such as wrinkles.