EUVIMEDEUVIMED entdecken
Crossref

Tri-attention complex-valued CNN for multimodal holographic digital human interaction

Xuan-Ye Wang, Yu Zhao, Zhong Xu, Liu-Ying Zhu, Meng Xie, Ting-Yu Zhang, Yanling Piao

Optics Express · 01.06.2026 · 34 (11) · 20473

DOI: 10.1364/oe.598892 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 26.05.2026. Verfasst von Xuan-Ye Wang und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Holography. Die Arbeit nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Holographic displays show great potential in immersive applications such as AR/VR; however, it still faces challenges in the generation quality of full-color computer-generated holography (CGH), visual perception consistency, and real-time interaction. This paper proposes a multimodal voice-interactive holographic digital human avatar system. The system relies on an RGB-D digital human avatar generated by AIGC technology, enabling personalized configurations such as outfit changes, personality simulation, and voice cloning, thus realizing end-to-end RGB-D generation. We adopt an end-to-end semantic interaction architecture of “ASR + Dual-LLM + TTS” to construct a multi-agent interactive system, achieving high-quality real-time voice interaction. To achieve high-fidelity full-color holographic reconstruction, we propose a Tri-Attention Complex-valued Convolutional Neural Network (TA-CCNN). This network introduces a third-dimensional Energy-Aware branch to build a three-branch parallel attention mechanism, which significantly enhances the contrast in high-energy regions (such as the eyes and facial features), improving color reproduction and ultimately presenting superior visual effects with deep backgrounds and vivid colors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HolographyHumansConvolutional Neural NetworksAvatarColor

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, X. Y., Zhao, Y., Xu, Z., Zhu, L. Y., Xie, M., Zhang, T. Y., & Piao, Y. (2026). Tri-attention complex-valued CNN for multimodal holographic digital human interaction. Optics Express, 34(11), 20473. https://doi.org/10.1364/oe.598892

Vancouver

Wang XY, Zhao Y, Xu Z, Zhu LY, Xie M, Zhang TY, et al. Tri-attention complex-valued CNN for multimodal holographic digital human interaction. Optics Express. 2026;34(11):20473. doi:10.1364/oe.598892

BibTeX
@article{Wang2026,
  author = {Wang, Xuan-Ye and Zhao, Yu and Xu, Zhong and Zhu, Liu-Ying and Xie, Meng and Zhang, Ting-Yu and Piao, Yanling},
  title = {Tri-attention complex-valued CNN for multimodal holographic digital human interaction},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {11},
  pages = {20473},
  doi = {10.1364/oe.598892}
}
Kostenlos starten →