Fast and deep deformation approximations

Abstract

Character rigs are procedural systems that compute the shape of an animated character for a given pose. They can be highly complex and must account for bulges, wrinkles, and other aspects of a character's appearance. When comparing film-quality character rigs with those designed for real-time applications, there is typically a substantial and readily apparent difference in the quality of the mesh deformations. Real-time rigs are limited by a computational budget and often trade realism for performance. Rigs for film do not have this same limitation, and character riggers can make the rig as complicated as necessary to achieve realistic deformations. However, increasing the rig complexity slows rig evaluation, and the animators working with it can become less efficient and may experience frustration. In this paper, we present a method to reduce the time required to compute mesh deformations for film-quality rigs, allowing better interactivity during animation authoring and use in real-time games and applications. Our approach learns the deformations from an existing rig by splitting the mesh deformation into linear and nonlinear portions. The linear deformations are computed directly from the transformations of the rig's underlying skeleton. We use deep learning methods to approximate the remaining nonlinear portion. In the examples we show from production rigs used to animate lead characters, our approach reduces the computational time spent on evaluating deformations by a factor of 5X-10X. This significant savings allows us to run the complex, film-quality rigs in real-time even when using a CPU-only implementation on a mobile device.

Latent‐space Dynamics for Reduced Deformable Simulation

“…As for layer size and count, we found that two hidden layers of width 100 provided the best tradeoff between training accuracy and simulation speed as can be seen in Figure 6. This result mirrors that of other recent works such as [BODO18] which found only two layers to be sufficient after PCA reduction.…”

Learning‐Based Animation of Clothing for Virtual Try‐On

“…Data‐Driven Models. Multiple works, both well established [LCF00, SRIC01] and recent [BODO18, CO18], propose to model surface deformations as a function of pose. Similar to them, some existing data‐driven methods for clothing animation also use the underlying kinematic skeletal model to drive the garment deformation [KV08, WHRO10, GRH*12, XUC*14, HTC*14].…”

High-Quality Face Capture Using Anatomical Muscles

“…Finally, one of the more philosophical questions in deep learning seems to revolve around what should or should not be considered a "learning crime" (drawing similarities to variational crimes [45]). For example, in [2], the authors learn a perturbation of linear blend skinning as opposed to the whole shape, assuming that the perturbation is lowerdimensional, spatially correlated, and/or easier to learn. The authors in [18,41] use spatially correlated networks for spatially correlated information under the assumption, once again, that this leads to a network that is easier to train and generalizes better.…”