App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 1

Latent code modulation and hierarchical cyclic constraints for face pose redirection

Liu Jiaxin1
Sun Peng1
Lang Yubo1
Shen Zhe2
Li Feixiang3
Zhou Chunbing1
1. School of Public Security Information Technology and Intelligence, Criminal Investigation Police University of China, Shenyang 110854, China
2. Civil Aviation College, Shenyang Aerospace University, Shenyang 110135, China
3. The 8th Brigade of Criminal Investigation Detachment, Dongguan Public Security Bureau, Dongguan Guangdong 523000, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0116

Abstract

Current face pose redirection methods suffer from limited pose diversity, high computational complexity, and poor identity consistency, and thus fail to meet practical face editing demands. To address these issues, this article presents a novel face pose redirection method based on latent code modulation and hierarchical recurrent constraint, which realizes controllable face pose editing via reference pose driving. First, the method adopts a hierarchical recurrent constraint strategy. According to the hierarchical semantic characteristics of the StyleGANv2 generator, the method divides latent codes into pose-related codes and appearance-related codes. Integrated with recurrent consistency constraints, the strategy drives the model to focus exclusively on pose feature learning and avoids the loss of facial identity information. Second, the method develops a Transformer-based pose code interaction module. Two stacked multi-head cross-attention layers achieve coarse-and-fine-grained collaborative aggregation of pose information, realize decoupled control of pose semantics, and generate robust pose guidance vectors. Finally, the method builds a modulation fusion module. In accordance with pose differences between input and reference images, affine transformation and gated fusion mechanisms dynamically adjust editing intensity and improve the accuracy of face pose redirection. Extensive experiments on the FFHQ dataset demonstrate that the proposed method effectively preserves facial identity information during pose redirection and outperforms state-of-the-art methods in both subjective and objective evaluation metrics.

Foundation Support

辽宁省教育厅科技创新团队项目(LJ222410175007)
辽宁省研究生教育教学改革研究资助项目(LNYJG2023317)
沈阳市科技计划项目社会治理科技专项(24-213-3-41)
校级重点攻关计划项目(ZDGGJH2507)
中国刑事警察学院研究生创新能力提升项目(2024YCYB33)
中国刑事警察学院研究生创新能力提升项目(2024YCYB53)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0116
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 1

Publish History

[2026-09-14] Accepted Paper

Cite This Article

刘佳鑫, 孙鹏, 郎宇博, 等. 基于隐编码调制与分层循环约束的人脸姿态转向方法 [J]. 计算机应用研究, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0116. (Liu Jiaxin, Sun Peng, Lang Yubo, et al. Latent code modulation and hierarchical cyclic constraints for face pose redirection [J]. Application Research of Computers, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0116. )

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
  • 2020-2022 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)