arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.06285cs.CVcs.GR
收藏

神经服装动态超分辨率

Neural Garment Dynamic Super-Resolution

School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院)

Meng Zhang, Jun Li

AI总结:

针对高分辨率服装仿真计算成本高的问题,提出基于学习的轻量级动态超分辨率方法,结合网格图网络与超网络生成细粒度褶皱,泛化性强且效果优于现有方法。

摘要:

由于计算需求较高,实现高效、高保真的高分辨率服装仿真是一项挑战。相比之下,低分辨率服装仿真更易实现,适用于智能手机等低配置设备。本文提出一种轻量级的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仿真中的高分辨率、高频细节。 该方法以低分辨率服装仿真和底层人体运动为输入,利用网格图网络(mesh-graph-net)基于粗糙服装动态和服装-人体交互计算超分辨率特征。随后,超网络(hyper-net)利用这些特征为每个粗糙网格三角形构建细节褶皱残差的隐式函数。考虑到粗糙服装形状对细节褶皱效果的影响,我们对粗糙服装形状进行校正,并通过这些隐式函数预测细节褶皱残差。最后,将细节褶皱残差应用于校正后的粗糙服装,生成细节丰富的高分辨率服装几何形状。 该方法可通过将预测结果迭代作为后续帧的输入实现滚动预测,生成细粒度褶皱细节以增强低分辨率仿真效果。尽管仅在小数据集上训练,该网络仍能稳健泛化至训练数据中未出现的不同体型、运动和服装类型。实验表明,该方法相比现有最优方案有显著提升,尤其在增强高频细粒度褶皱细节质量方面表现突出。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑