Spatially Adaptive Cloth Regression with Implicit Neural Representations
This addresses the problem of high computational demands and complex methodologies in cloth simulation for computer graphics applications, representing an incremental improvement with novel components.
The paper tackles the challenge of accurately representing fine-detailed cloth wrinkles in computer graphics by introducing an anisotropic cloth regression technique using implicit neural representations, which consistently surpasses traditional discrete representations in modeling localized wrinkles under the same memory constraints.
The accurate representation of fine-detailed cloth wrinkles poses significant challenges in computer graphics. The inherently non-uniform structure of cloth wrinkles mandates the employment of intricate discretization strategies, which are frequently characterized by high computational demands and complex methodologies. Addressing this, the research introduced in this paper elucidates a novel anisotropic cloth regression technique that capitalizes on the potential of implicit neural representations of surfaces. Our first core contribution is an innovative mesh-free sampling approach, crafted to reduce the reliance on traditional mesh structures, thereby offering greater flexibility and accuracy in capturing fine cloth details. Our second contribution is a novel adversarial training scheme, which is designed meticulously to strike a harmonious balance between the sampling and simulation objectives. The adversarial approach ensures that the wrinkles are represented with high fidelity, while also maintaining computational efficiency. Our results showcase through various cloth-object interaction scenarios that our method, given the same memory constraints, consistently surpasses traditional discrete representations, particularly when modelling highly-detailed localized wrinkles.