ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

High-quality computer-generated holography based on Vision Mamba

Yang, Lei*; Xu, Shengyuan; Yang, Chunzheng; Chang, Chenliang; Hou, Qichao; Song, Qiang江苏大学
Optics and Lasers in Engineering2025-1DOI: 10.1016/j.optlaseng.2024.108704
4阅读
引用收藏
分享

摘要

Deep learning, especially through model-driven unsupervised networks, offers a novel approach for efficient computer-generated hologram (CGH) generation. However, current model-driven CGH generation models are primarily built on the convolutional neural networks (CNNs), which struggle to achieve high-quality hologram reconstruction due to limited receptive fields. Although Vision Transformers (ViTs) excel at processing more distant visual information, they are burdened with huge computational load. The recent emergence of Vision Mamba (ViM) presents a promising avenue to address these challenges. In this study, we introduce the CVMNet, a lightweight model that combines the precision of convolutional layers for local feature extraction and the longrange modeling abilities of state-space models (SSMs) to enhance the quality of CGHs. By employing parallel computation for the ViM to handle feature channels, the CVMNet effectively reduces the number of model parameters. Numerical reconstruction and optical experiments demonstrate that the CVMNet can generate 1080P high-quality holograms in just 16 ms, boosting an average PSNR of over 30 dB and effectively suppressing speckle noise in reconstructed images. Additionally, the CVMNet showcases robust generalization capabilities.

学科与关键词

关键词
Computer-generated holographyDeep learningVision mambaParallel computationLong-range modeling
相关
加载中…
  • Complex-valued generative adversarial network for real-time and high-quality computer-generated holography
    Qin, Haifeng; Han, Chao*; Shi, Xuan; Gu, Tao; Sun, KangshengOptics Express, 2024, 32(25): 44437-44451.
  • 3D-CGH-Net: Customizable 3D-hologram generation via deep learning
    Rymov, Dmitry A.; Svistunov, Andrey S.; Starikov, Rostislav S.; Shifrina, Anna V.; Rodin, Vladislav G.; Evtikhiev, Nikolay N.; Cheremkhin, Pavel A.*Optics and Lasers in Engineering, 2025, 184: 108645.
  • Non-convex optimization for inverse problem solving in computer-generated holography
    Sui, Xiaomeng; He, Zehao; Chu, Daping*; Cao, Liangcai*Light-Science & Applications, 2024, 13(1): 158.被引 5
查看全部 →

发表信息

论文状态
公开发表
期刊
Optics and Lasers in Engineering
发表日期
2025-01
卷期
第 184 卷
页码
108704
DOI
10.1016/j.optlaseng.2024.108704
语言
MULTI-LANGUAGE
成果收录
SCIE
资助标注
Postdoctoral Science Foundation of Jiangsu Province, China [2020Z016]

作者

  • Y

    Yang, Lei (通讯) (第一作者)

    jiangsu univ

  • X

    Xu, Shengyuan

    jiangsu univ

查看全部 6 位作者收起作者
  • Y

    Yang, Chunzheng

    jiangsu univ

  • C

    Chang, Chenliang

    univ shanghai sci & technol

  • H

    Hou, Qichao

    hunan univ

  • S

    Song, Qiang

    hunan univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417