We introduce FOF-X for real-time reconstruction of detailed human geometry from a single image. Balancing real-time speed against high-quality results is a persistent challenge, mainly due to the high computational demands of existing 3D representations. To address this, we propose Fourier Occupancy Field (FOF), an efficient 3D representation by learning the Fourier series. The core of FOF is to factorize a 3D occupancy field into a 2D vector field, retaining topology and spatial relationships within the 3D domain while facilitating compatibility with 2D convolutional neural networks. Such a representation bridges the gap between 3D and 2D domains, enabling the integration of human parametric models as priors and enhancing the reconstruction robustness. Based on FOF, we design a new reconstruction framework, FOF-X, to avoid the performance degradation caused by texture and lighting. This enables our real-time reconstruction system to better handle the domain gap between training images and real images. Additionally, in FOF-X, we enhance the inter-conversion algorithms between FOF and mesh representations with a Laplacian constraint and an automaton-based discontinuity matcher, improving both quality and robustness. We validate the strengths of our approach on different datasets and real-captured data, where FOF-X achieves new state-of-the-art results. The code has already been released for research purposes at https://cic.tju.edu.cn/faculty/likun/projects/FOFX/index.html.

翻译：本文提出FOF-X，用于从单张图像实时重建精细人体几何。在实时速度与高质量结果之间取得平衡始终是一项挑战，这主要源于现有三维表示方法的高计算需求。为解决此问题，我们提出傅里叶占据场（FOF），一种通过学习傅里叶级数实现的高效三维表示方法。FOF的核心思想是将三维占据场分解为二维向量场，在保留三维域内拓扑结构与空间关系的同时，提升其与二维卷积神经网络的兼容性。该表示方法弥合了三维与二维领域之间的鸿沟，使得人体参数化模型可作为先验知识融入系统，从而增强重建的鲁棒性。基于FOF，我们设计了新的重建框架FOF-X，以规避由纹理和光照引起的性能下降。这使得我们的实时重建系统能够更好地处理训练图像与真实图像之间的域差异。此外，在FOF-X中，我们通过引入拉普拉斯约束和基于自动机的不连续性匹配器，改进了FOF与网格表示之间的相互转换算法，从而提升了重建质量与鲁棒性。我们在多个数据集及实际采集数据上验证了所提方法的优势，FOF-X取得了当前最优的性能。相关代码已发布于https://cic.tju.edu.cn/faculty/likun/projects/FOFX/index.html 供研究使用。