Gaussian digital human reconstruction based on region enhancement and multi-layer lora

Zhu Rui
He Hong
Xiao Huiqian
Jin Wei
Liu Qian
Xie Weijiang
Chen Baili
School of Health Science & Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Abstract

To address insufficient recovery of local high-frequency details, including clothing textures and hair boundaries, and limited appearance adaptation in monocular digital human reconstruction, GALA-GS employed multi-layer low-rank adaptation (LoRA) in UV-related decoding modules and the Refiner to learn identity-specific appearance with limited additional parameters. It introduced a geometry- and opacity-aware adaptive region enhancement loss (GO-AREL) to strengthen supervision over upper-body and hair regions. Under a unified single-image driving protocol on ZJU-MoCap, GALA-GS achieved 27.842 dB PSNR, 0.9204 SSIM, 0.0440 LPIPS, and 0.012 MAE. On a local six-identity subset of GeneBody, it achieved 25.784 dB PSNR, 0.9338 SSIM, 0.0463 LPIPS, and 0.012 MAE. These results show that GALA-GS improves local-detail reconstruction while retaining a low trainable-parameter overhead under the adopted single-image driving and unified evaluation protocols.

Foundation Support

本文受国家科学技术部项目(G2021013008)
中国高校产学研创新基金资助项目(2023RY011)
教师发展研究重点项目(CFTD2025ZD08)
华为AI算力加速计划项目

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.06.0188
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 2

Publish History

[2026-10-24] Accepted Paper

Cite This Article

朱睿, 何宏, 肖惠谦, 等. 基于区域增强与多层LoRA的高斯数字人重建 [J]. 计算机应用研究, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.06.0188. (Zhu Rui, He Hong, Xiao Huiqian, et al. Gaussian digital human reconstruction based on region enhancement and multi-layer lora [J]. Application Research of Computers, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.06.0188. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.


Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2025 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)