Acta Optica Sinica, Volume. 44, Issue 10, 1026027(2024)

Image Synthesis of Compressive Light Field Displays with U-Net

Chen Gao1,2, Xiaodi Tan3,4,5、*, Haifeng Li6, and Xu Liu6
Author Affiliations
  • 1College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350117, Fujian , China
  • 2Fujian Provincial Key Laboratory of Photonics Technology, Fuzhou 350117, Fujian , China
  • 3Key Laboratory of Optoelectronic Science and Technology for Medicine of Ministry of Education, Fuzhou 350117, Fujian , China
  • 4Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application, Fuzhou 350117, Fujian , China
  • 5Information Photonics Research Center, Fujian Normal University, Fuzhou 350117, Fujian , China
  • 6College of Optical Science and Engineering, Zhejiang University, Hangzhou 310027, Zhejiang , China
  • show less
    References(32)

    [1] Hancock P A, Sawyer B D, Stafford S. The effects of display size on performance[J]. Ergonomics, 58, 337-354(2015).

    [2] Gao C, Li Z Y, Wu R M et al. Development and prospect of portable three-dimensional displays[J]. Laser & Optoelectronics Progress, 60, 0811009(2023).

    [3] Qiao W, Zhou F B, Chen L S. Towards application of mobile devices: the status and future of glasses-free 3D display[J]. Infrared and Laser Engineering, 49, 0303002(2020).

    [4] Wetzstein G, Lanman D, Heidrich W et al. Layered 3D: tomographic image synthesis for attenuation-based light field and high dynamic range displays[J]. ACM Transactions on Graphics, 30, 95(2011).

    [5] Heide F, Lanman D, Reddy D et al. Cascaded displays: spatiotemporal superresolution using offset pixel layers[J]. ACM Transactions on Graphics, 33, 60(2014).

    [6] Kreinovich V Y. Arbitrary nonlinearity is sufficient to represent all functions by neural networks: a theorem[J]. Neural Networks, 4, 381-383(1991).

    [7] Xiao L, Kaplanyan A, Fix A et al. DeepFocus: learned image synthesis for computational displays[J]. ACM Transactions on Graphics, 37, 200(2018).

    [8] Choi S, Gopakumar M, Peng Y F et al. Time-multiplexed neural holography: a flexible framework for holographic near-eye displays with fast heavily-quantized spatial light modulators[C], 1-9(2022).

    [9] Chang C L, Dai B, Xia J et al. Review of holographic near-eye displays for visual comfort[J]. Laser & Optoelectronics Progress, 59, 2011001(2022).

    [10] Liu J, Pi D P, Wang Y T. Research progress of real-time holographic 3D display technology[J]. Acta Optica Sinica, 43, 1509001(2023).

    [11] 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, 6, 220135(2023).

    [12] Zheng H D, Peng J C, Wang Z et al. Diffraction model-driven neural network trained using hybrid domain loss for real-time and high-quality computer-generated holography[J]. Optics Express, 31, 19931-19944(2023).

    [13] Ren H, Wang Q H, Xing Y et al. Super-multiview integral imaging scheme based on sparse camera array and CNN super-resolution[J]. Applied Optics, 58, A190-A196(2019).

    [14] Yu X B, Li H Y, Sang X Z et al. Aberration correction based on a pre-correction convolutional neural network for light-field displays[J]. Optics Express, 29, 11009-11020(2021).

    [15] Maruyama K, Takahashi K, Fujii T. Comparison of layer operations and optimization methods for light field display[J]. IEEE Access, 8, 38767-38775(2020).

    [16] He K M, Zhang X Y, Ren S Q et al. Deep residual learning for image recognition[C], 770-778(2016).

    [17] Zheng Q, Babaei V, Wetzstein G et al. Neural light field 3D printing[J]. ACM Transactions on Graphics, 39, 207(2020).

    [18] Mildenhall B, Srinivasan P P, Tancik M et al. NeRF: representing scenes as neural radiance fields for view synthesis[J]. Communications of the ACM, 65, 99-106(2022).

    [19] Sun Y F, Li Z, Wang S Z et al. Depth-assisted calibration on learning-based factorization for a compressive light field display[J]. Optics Express, 31, 5399-5413(2023).

    [20] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[M]. Navab N, Hornegger J, Wells W M, et al. Medical image computing and computer-assisted intervention-MICCAI 2015, 9351, 234-241(2015).

    [21] Wetzstein G, Lanman D, Hirsch M et al. Tensor displays: compressive light field synthesis using multilayer displays with directional backlighting[J]. ACM Transactions on Graphics, 31, 80(2012).

    [22] Lee S, Jang C, Moon S et al. Additive light field displays: realization of augmented reality with holographic optical elements[J]. ACM Transactions on Graphics, 35, 60(2016).

    [23] Lanman D, Wetzstein G, Hirsch M et al. Polarization fields: dynamic light field display using multi-layer LCDs[J]. ACM Transactions on Graphics, 30, 186(2011).

    [24] Zhang J H, Fan Z C, Sun D W et al. Unified mathematical model for multilayer-multiframe compressive light field displays using LCDs[J]. IEEE Transactions on Visualization and Computer Graphics, 25, 1603-1614(2019).

    [25] Lanman D, Hirsch M, Kim Y et al. Content-adaptive parallax barriers: optimizing dual-layer 3D displays using low-rank light field factorization[J]. ACM Transactions on Graphics, 29, 163(2010).

    [26] Wetzstein G, Lanman D, Hirsch M et al. Real-time image generation for compressive light field displays[J]. Journal of Physics: Conference Series, 415, 012045(2013).

    [27] Kim D, Lee S, Moon S et al. Hybrid multi-layer displays providing accommodation cues[J]. Optics Express, 26, 17170-17184(2018).

    [28] Zhu L M, Du G, Lü G Q et al. Performance improvement for compressive light field display with multi-plane projection[J]. Optics and Lasers in Engineering, 142, 106609(2021).

    [29] Liu M L, Lu C H, Li H F et al. Bifocal computational near eye light field displays and structure parameters determination scheme for bifocal computational display[J]. Optics Express, 26, 4060-4074(2018).

    [30] Jo N Y, Lim H G, Lee S K et al. Depth enhancement of multi-layer light field display using polarization dependent internal reflection[J]. Optics Express, 21, 29628-29636(2013).

    [31] He K M, Zhang X Y, Ren S Q et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification[C], 1026-1034(2015).

    [32] Vanholder H. Efficient inference with tensorRT[C], 1-24(2016).

    Tools

    Get Citation

    Copy Citation Text

    Chen Gao, Xiaodi Tan, Haifeng Li, Xu Liu. Image Synthesis of Compressive Light Field Displays with U-Net[J]. Acta Optica Sinica, 2024, 44(10): 1026027

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Physical Optics

    Received: Oct. 20, 2023

    Accepted: Dec. 1, 2023

    Published Online: May. 6, 2024

    The Author Email: Tan Xiaodi (xtan@fjnu.edu.cn)

    DOI:10.3788/AOS231683

    CSTR:32393.14.AOS231683

    Topics