Achieving efficient, high-fidelity, high-resolution garment simulation is challenging due to its computational demands. Conversely, low-resolution garment simulation is more accessible and ideal for low-budget devices like smartphones. In this paper, we introduce a lightweight, learning-based method for garment dynamic super-resolution, designed to efficiently enhance high-resolution, high-frequency details in low-resolution garment simulations. Starting with low-resolution garment simulation and underlying body motion, we utilize a mesh-graph-net to compute super-resolution features based on coarse garment dynamics and garment-body interactions. These features are then used by a hyper-net to construct an implicit function of detailed wrinkle residuals for each coarse mesh triangle. Considering the influence of coarse garment shapes on detailed wrinkle performance, we correct the coarse garment shape and predict detailed wrinkle residuals using these implicit functions. Finally, we generate detailed high-resolution garment geometry by applying the detailed wrinkle residuals to the corrected coarse garment. Our method enables roll-out prediction by iteratively using its predictions as input for subsequent frames, producing fine-grained wrinkle details to enhance the low-resolution simulation. Despite training on a small dataset, our network robustly generalizes to different body shapes, motions, and garment types not present in the training data. We demonstrate significant improvements over state-of-the-art alternatives, particularly in enhancing the quality of high-frequency, fine-grained wrinkle details.

翻译：实现高效、高保真、高分辨率的服装模拟因其计算需求而具有挑战性。相反，低分辨率服装模拟更为可行，且适用于智能手机等低预算设备。本文提出一种轻量级、基于学习的服装动态超分辨率方法，旨在高效增强低分辨率服装模拟中的高分辨率、高频细节。我们从低分辨率服装模拟和底层身体运动出发，利用网格图网络基于粗糙服装动态及服装-身体交互计算超分辨率特征。随后，一个超网络利用这些特征为每个粗糙网格三角形构建详细褶皱残差的隐式函数。考虑到粗糙服装形状对详细褶皱表现的影响，我们修正粗糙服装形状，并使用这些隐式函数预测详细褶皱残差。最后，通过将详细褶皱残差应用于修正后的粗糙服装，生成详细的高分辨率服装几何。我们的方法通过迭代使用其预测作为后续帧的输入，实现滚动预测，从而生成细粒度褶皱细节以增强低分辨率模拟。尽管在小型数据集上训练，我们的网络能够稳健地泛化到训练数据中未出现的不同体型、运动及服装类型。我们证明了相较于现有先进方法的显著改进，特别是在增强高频、细粒度褶皱细节的质量方面。