HiLo：利用参数模型的高低频信息进行精细且鲁棒的3D穿衣人体重建
HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
AI总结：
提出HiLo方法，利用参数模型的高频信息增强几何细节、低频信息提升鲁棒性，实现精细且鲁棒的3D穿衣人体重建，在Thuman2.0和CAPE数据集上显著优于现有方法。
摘要：
重建3D穿衣人体涉及创建穿着衣物个体的精细几何形状，其应用范围从虚拟试穿、电影到游戏。为了实现实用且广泛的应用，近期进展提出从RGB图像生成穿衣人体。然而，这些方法难以同时重建精细且鲁棒的虚拟形象。我们通过实验发现，参数模型中的高频（HF）和低频（LF）信息分别有潜力增强几何细节并提高对噪声的鲁棒性。基于此，我们提出HiLo，即利用高低频信息进行穿衣人体重建，其包含两个组件。1）为了利用HF信息恢复精细几何，我们提出一种渐进式HF符号距离函数，以增强穿衣人体的精细3D几何。我们分析得出，我们的渐进学习方式缓解了阻碍模型收敛的大梯度。2）为了利用LF信息实现对参数模型不准确估计的鲁棒重建，我们提出一种空间交互隐式函数。该函数有效利用了参数模型低分辨率体素网格中的互补空间信息。实验结果表明，在Thuman2.0和CAPE数据集上，HiLo在倒角距离上分别比最先进的方法提高了10.43%和9.54%。此外，HiLo展示了对参数模型噪声、挑战性姿态和各种服装风格的鲁棒性。
英文摘要：
Reconstructing 3D clothed human involves creating a detailed geometry of individuals in clothing, with applications ranging from virtual try-on, movies, to games. To enable practical and widespread applications, recent advances propose to generate a clothed human from an RGB image. However, they struggle to reconstruct detailed and robust avatars simultaneously. We empirically find that the high-frequency (HF) and low-frequency (LF) information from a parametric model has the potential to enhance geometry details and improve robustness to noise, respectively. Based on this, we propose HiLo, namely clothed human reconstruction with high- and low-frequency information, which contains two components. 1) To recover detailed geometry using HF information, we propose a progressive HF Signed Distance Function to enhance the detailed 3D geometry of a clothed human. We analyze that our progressive learning manner alleviates large gradients that hinder model convergence. 2) To achieve robust reconstruction against inaccurate estimation of the parametric model by using LF information, we propose a spatial interaction implicit function. This function effectively exploits the complementary spatial information from a low-resolution voxel grid of the parametric model. Experimental results demonstrate that HiLo outperforms the state-of-the-art methods by 10.43% and 9.54% in terms of Chamfer distance on the Thuman2.0 and CAPE datasets, respectively. Additionally, HiLo demonstrates robustness to noise from the parametric model, challenging poses, and various clothing styles.
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。
