Holographic Image Distortion Correction Based on Multi-Branch-Fused Complex-Valued Neural Network

CHEN Yi-fei; LIU Yan-wei; LIU Jin-xia; GU Xiao-yan

doi:10.12263/DZXB.20250549

您当前的位置：

首页 >

文章列表页 >

Holographic Image Distortion Correction Based on Multi-Branch-Fused Complex-Valued Neural Network

PAPERS | 更新时间：2025-12-27

- Holographic Image Distortion Correction Based on Multi-Branch-Fused Complex-Valued Neural Network
- ACTA ELECTRONICA SINICA Vol. 53, Issue 9, Pages: 3319-3330(2025)
- 作者机构：
  
  1.中国科学院信息工程研究所，北京 100085
  2.中国科学院大学网络空间安全学院，北京 101408
  3.网络空间安全防御全国重点实验室，北京 100085
  4.浙江万里学院，浙江宁波 315100
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62371450)
- DOI：10.12263/DZXB.20250549
  CLC： TP391.41;TP18
- Received：24 June 2025，
  
  Accepted：05 September 2025，
  
  Published：25 September 2025
- 稿件说明：
移动端阅览
陈逸飞, 刘延伟, 刘金霞, 等. 基于多分支融合复数网络的全息图像失真矫正[J]. 电子学报, 2025, 53(09): 3319-3330.

CHEN Yi-fei, LIU Yan-wei, LIU Jin-xia, et al. Holographic Image Distortion Correction Based on Multi-Branch-Fused Complex-Valued Neural Network[J]. Acta Electronica Sinica, 2025, 53(09): 3319-3330.
陈逸飞, 刘延伟, 刘金霞, 等. 基于多分支融合复数网络的全息图像失真矫正[J]. 电子学报, 2025, 53(09): 3319-3330. DOI：10.12263/DZXB.20250549

CHEN Yi-fei, LIU Yan-wei, LIU Jin-xia, et al. Holographic Image Distortion Correction Based on Multi-Branch-Fused Complex-Valued Neural Network[J]. Acta Electronica Sinica, 2025, 53(09): 3319-3330. DOI：10.12263/DZXB.20250549

摘要

全息显示技术可以再现出包含物体全部信息的三维成像，能为用户带来高度逼真的视觉体验，被认为是目前最理想的裸眼三维显示技术.全息显示带来的独特三维沉浸式体验使得全息通信在医疗、教育、虚拟现实等领域具有广泛的应用前景.但全息通信技术的大规模商业化应用还面临众多问题.其中，影响全息通信质量的一个主要问题就是在通信过程中压缩噪声与信道干扰等导致的多重混叠失真.现有图像失真矫正技术大多聚焦单一失真类型，难以应对复杂场景下的全息混合失真问题，严重制约全息技术的实际应用效果.针对这一难题，本文提出一种基于多分支复数注意力网络的全息图像失真矫正方法，通过构建分层并行的多分支网络结构，实现对全息图像多尺度、多维度特征的深度提取与协同融合；同时提出复数域自适应注意力机制，强化网络对相位畸变、振幅衰减等关键失真特征的感知与抑制能力，从而实现对压缩、传输等全链路失真的精准矫正.在包含压缩和信道噪声等混合类型的全息失真矫正实验中，相较于现有先进的深度学习失真矫正方法SCUNet（Swin-Conv-UNet），本文方法在峰值信噪比指标上提升0.41 dB以上，结构相似性指标提升0.006以上，有效抑制了振幅失真导致的亮度异常，矫正了相位畸变，显著提升了全息图像的重建质量.

Abstract

Holographic display technology can reproduce three-dimensional imaging that encompasses all information of an object

providing users with a highly realistic visual experience. It is regarded as the most perfect naked-eye 3D display technology currently available. The unique immersive 3D experience offered by holographic displays gives holographic communication has broad application prospects in fields such as healthcare

education

and virtual reality. However

the large-scale commercial application of holographic communication technology still currently confronts numerous obstacles. Among them

one major issue affecting the quality of holographic communication is the multiple aliasing distortions caused by compression noise and channel interference during hologram transmission. Existing image distortion correction techniques mostly focus on single distortion type and struggle to address the problem of mixed holographic distortions in complex scenarios

severely limiting the effectiveness of holographic technology in the practical applications. To tackle this issue

this paper proposes a holographic image distortion correction method based on a multi-branch complex-valued convolutional neural network. This method constructs a multi-level parallel multi-branch network architecture to achieve in-depth extraction and collaborative fusion of multi-scale and multi-dimensional distortion features of holographic images. Simultaneously

a complex-valued adaptive attention mechanism is proposed to enhance the network’s perception and suppression capabilities for key distortion features such as phase distortion and amplitude attenuation

thereby achieving precise correction of end-to-end distortions caused during compression and transmission. In the experiments involving mixed-type holographic distortions including compression and channel noises

compared to the state-of-the-art deep learning distortion correction method SCUNet (Swin-Conv-UNet)

the proposed method achieves an average improvement of over 0.41 dB in peak signal-to-noise ratio (PSNR) and an average increase of over 0.006 in structural similarity index (SSIM). These experimental results show that the proposed method can effectively suppress the brightness abnormalities caused by amplitude distortion

correct the phase distortions

and significantly enhance the reconstruction quality of holographic images.

关键词

Keywords

references

LIU Z , MALEKIAN R , LI R , et al . Guest editorial: Holographic video communications [J ] . IEEE Wireless Communications , 2025 , 32 ( 2 ): 94 - 95 .

BLINDER D , AHAR A , BETTENS S , et al . Signal processing challenges for digital holographic video display systems [J ] . Signal Processing: Image Communication , 2019 , 70 : 114 - 130 .

CUERVO E . BEYOND REALITY: Head-mounted displays for mobile systems researchers [J ] . GetMobile: Mobile Computing and Communications , 2017 , 21 ( 2 ): 9 - 15 .

刘娟 , 皮大普 , 王涌天 . 实时全息三维显示技术研究进展 [J ] . 光学学报 , 2023 , 43 ( 15 ): 128 - 141 .

LIU J , PI D P , WANG Y T . Research progress of real-time holographic 3D display technology [J ] . Acta Optica Sinica , 2023 , 43 ( 15 ): 128 - 141 . (in Chinese)

LIU N H , LIU K X , YANG Y X , et al . Propagation-adaptive 4K computer-generated holography using physics-constrained spatial and Fourier neural operator [J ] . Nature Communications , 2025 , 16 : 7761 .

陈佳 , 刘上 , 郜帅 , 等 . 面向全息通信的智算融合网络 [J ] . 电子学报 , 2025 , 53 ( 3 ): 754 - 764 .

CHEN J , LIU S , GAO S , et al . Smart computing integration network for holographic communication [J ] . Acta Electronica Sinica , 2025 , 53 ( 3 ): 754 - 764 . (in Chinese)

朱原玮 , 黄亚坤 , 乔秀全 . 面向全息视频通信的自适应分块传输方法 [J ] . 电子学报 , 2024 , 52 ( 4 ): 1144 - 1154 .

ZHU Y W , HUANG Y K , QIAO X Q . Towards holographic video communications: An adaptive tiling solution [J ] . Acta Electronica Sinica , 2024 , 52 ( 4 ): 1144 - 1154 . (in Chinese)

JIAO S M , JIN Z , CHANG C L , et al . Compression of phase-only holograms with JPEG standard and deep learning [J ] . Applied Sciences , 2018 , 8 ( 8 ): 1258 .

SHIMOBABA T , BLINDER D , MAKOWSKI M , et al . Dynamic-range compression scheme for digital hologram using a deep neural network [J ] . Optics Letters , 2019 , 44 ( 12 ): 3038 - 3041 .

HU C C , YANG G L , XIE H Y . 3D information transmission of a computer-generated hologram using a quantum compensation hybrid neural network [J ] . Optics Express , 2024 , 32 ( 13 ): 23736 - 23749 .

JEE M , KIM H , YOON M , et al . Hologram super-resolution using dual-generator GAN [C ] // 2022 IEEE International Conference on Image Processing . Piscataway : IEEE , 2022 : 2596 - 2600 .

BOURTSOULATZE E , BURTH KURKA D , GÜNDÜZ D . Deep joint source-channel coding for wireless image transmission [J ] . IEEE Transactions on Cognitive Communications and Networking , 2019 , 5 ( 3 ): 567 - 579 .

LEFKIMMIATIS S . Universal denoising networks: A novel CNN architecture for image denoising [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3204 - 3213 .

白勇强 , 禹晶 , 李一秾 , 等 . 基于深度先验的盲图像去模糊算法 [J ] . 电子学报 , 2023 , 51 ( 4 ): 1050 - 1067 .

BAI Y Q , YU J , LI Y N , et al . Deep prior-based blind image deblurring [J ] . Acta Electronica Sinica , 2023 , 51 ( 4 ): 1050 - 1067 . (in Chinese)

YANG X H , XU Y , QUAN Y H , et al . Image denoising via sequential ensemble learning [J ] . IEEE Transactions on Image Processing , 2020 , 29 : 5038 - 5049 .

HONG Z W , FAN X C , JIANG T , et al . End-to-end unpaired image denoising with conditional adversarial networks [C ] // 2020 Proceedings of the AAAI Conference on Artificial Intelligence . California : AAAI , 2020 : 4140 - 4149 .

ZHANG K , ZUO W M , CHEN Y J , et al . Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising [J ] . IEEE Transactions on Image Processing , 2017 , 26 ( 7 ): 3142 - 3155 .

TAI Y , YANG J , LIU X M , et al . MemNet: A persistent memory network for image restoration [C ] // 2017 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 4549 - 4557 .

QUAN Y H , CHEN Y X , SHAO Y Z , et al . Image denoising using complex-valued deep CNN [J ] . Pattern Recognition , 2021 , 111 : 107639 .

TIAN C W , XU Y , ZUO W M . Image denoising using deep CNN with batch renormalization [J ] . Neural Networks , 2020 , 121 : 461 - 473 .

LIU S Q , LEI Y , ZHANG L Y , et al . MRDDANet: A multiscale residual dense dual attention network for SAR image denoising [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 5214213 .

TIAN C W , XU Y , ZUO W M , et al . Designing and training of a dual CNN for image denoising [J ] . Knowl. Based Syst. , 2020 , 226 : 106949 .

LEFKIMMIATIS S . Non-local color image denoising with convolutional neural networks [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 5882 - 5891 .

CHEN J W , CHEN J W , CHAO H Y , et al . Image blind denoising with generative adversarial network based noise modeling [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3155 - 3164 .

GUO S , YAN Z F , ZHANG K , et al . Toward convolutional blind denoising of real photographs [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 1712 - 1722 .

ZHANG K , LI Y W , LIANG J Y , et al . Practical blind image denoising via swin-conv-UNet and data synthesis [J ] . Machine Intelligence Research , 2023 , 20 ( 6 ): 822 - 836 .

LIU Z , LIN Y T , CAO Y , et al . Swin transformer: Hierarchical vision transformer using shifted windows [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2022 : 9992 - 10002 .

SZPYGIEL J , CHLIPALA M , KUKOLOWICZ R , et al . Distortion correction for wide angle holographic projector [J ] . Photonics Letters of Poland , 2021 , 13 ( 4 ): 79 - 81 .

HE Z H , SUI X M , JIN G F , et al . Distortion-correction method based on angular spectrum algorithm for holographic display [J ] . IEEE Transactions on Industrial Informatics , 2019 , 15 ( 11 ): 6162 - 6169 .

LI J H , ZHANG H L , JI Q L , et al . Distortion-corrected integral imaging 3D display system based on lens array holographic optical element [J ] . Symmetry , 2022 , 14 ( 7 ): 1481 .

SHI L , LI B C , KIM C , et al . Towards real-time photorealistic 3D holography with deep neural networks [J ] . Nature , 2021 , 591 ( 7849 ): 234 - 239 .

BOYCE J M , DORÉ R , DZIEMBOWSKI A , et al . MPEG immersive video coding standard [J ] . Proceedings of the IEEE , 2021 , 109 ( 9 ): 1521 - 1536 .

LIU K X , WU J C , HE Z H , et al . 4K-DMDNet: Diffraction model-driven network for 4K computer-generated holography [J ] . Opto-Electronic Advances , 2023 , 6 ( 5 ): 220135 .

LIU K X , WU J C , CAO L C . High-quality and high-speed computer-generated holography via deep-learning-assisted bidirectional error diffusion method [J ] . Optics Express , 2024 , 32 ( 21 ): 37342 - 37354 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰