FOF-X: Towards Real-time Detailed Human Reconstruction from a Single Image
- 22 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-11
Abstract
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.Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2023YFC3082100)
- National Natural Science Foundation of China (62125107)
This publication has 50 references indexed in Scilit:
- TeCH: Text-Guided Reconstruction of Lifelike Clothed Humans2024
- Monocular Real-Time Human Geometry Reconstruction2022
- Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel Classes2022
- STAR: Sparse Trained Articulated Human Body Regressor2020
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Monocular Real-Time Volumetric Performance Capture2020
- PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization2020
- Learning to Dress 3D People in Generative Clothing2020
- Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh Deformation2019
- Expressive Body Capture: 3D Hands, Face, and Body From a Single Image2019