Review of 3D Human Reconstruction Methods Empowering VR/AR

Authors

• Lisha Zhang, School of Informatics, Xiamen University, Xiamen 361102, China
• Yuchi Huo, Zhejiang University, Hangzhou 310027, China
• Qi Ye, Zhejiang University, Hangzhou 310027, China
• Anjun Chen, School of Informatics, Xiamen University, Xiamen 361102, China
• Shihui Guo, School of Informatics, Xiamen University, Xiamen 361102, China
• Jiming Chen, Zhejiang University, Hangzhou 310027, China

Abstract

Abstract: 3D human reconstruction is critical for VR/AR. Early methods relied on multi-view cameras and depth sensors but were costly. Mid-term approaches using parametric human models enabled efficient single-image reconstruction, while implicit neural representations improved fidelity yet suffered from low efficiency. Currently, 3D Gaussian Splatting achieves high accuracy and real-time rendering as a new paradigm. Challenges include detail distortion and limited generalization, and future development will focus on VR/AR integration.

Recommended Citation

Zhang, Lisha; Huo, Yuchi; Ye, Qi; Chen, Anjun; Guo, Shihui; and Chen, Jiming (2026) "Review of 3D Human Reconstruction Methods Empowering VR/AR," Journal of System Simulation: Vol. 38: Iss. 3, Article 1.
DOI: 10.16182/j.issn1004731x.joss.25-1056
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss3/1

First Page

545

Last Page

562

CLC

TP319.9

Recommended Citation

Zhang Lisha, Huo Yuchi, Ye Qi, et al. Review of 3D Human Reconstruction Methods Empowering VR/AR[J]. Journal of System Simulation, 2026, 38(3): 545-562.

Corresponding Author

Chen Anjun

DOI

10.16182/j.issn1004731x.joss.25-1056