基于U-Net的压缩光场显示图案生成方法  

Image Synthesis of Compressive Light Field Displays with U-Net

作　　者：高晨 谭小地 李海峰[6] 刘旭[6] Gao Chen;Tan Xiaodi;Li Haifeng;Liu Xu(College of Photonic and Electronic Engineering,Fujian Normal University,Fuzhou 350117,Fujian,China;Fujian Provincial Key Laboratory of Photonics Technology,Fuzhou 350117,Fujian,China;Key Laboratory of Optoelectronic Science and Technology for Medicine of Ministry of Education,Fuzhou 350117,Fujian,China;Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application,Fuzhou 350117,Fujian,China;Information Photonics Research Center,Fujian Normal University,Fuzhou 350117,Fujian,China;College of Optical Science and Engineering,Zhejiang University,Hangzhou 310027,Zhejiang,China)

机构地区：[1]福建师范大学光电与信息工程学院,福建福州350117 [2]福建省光子技术重点实验室,福建福州350117 [3]医学光电科学与技术教育部重点实验室,福建福州350117 [4]福建省光电传感应用工程技术研究中心,福建福州350117 [5]福建师范大学信息光子学研究中心,福建福州350117 [6]浙江大学光电科学与工程学院,浙江杭州310027

出　　处：《光学学报》2024年第10期366-384,共19页Acta Optica Sinica

基　　金：国家自然科学基金(U22A2080);国家重点研发计划(2018YFA0701800);福建省科技重大专项(2020HZ01012)。

摘　　要：压缩光场显示具有结构简单紧凑、显示空间分辨率高的优点,但求解压缩光场显示图案的迭代算法存在计算量大的问题。随着人工智能技术的发展,基于深度学习的图像生成算法也被应用到三维显示中。提出一种将计算机视觉中执行图像分割任务的U-Net作为优化压缩光场显示图案的网络模型。根据给定的观看角度生成几组经过数据增强的目标光场数据集作为U-Net的训练集;在U-Net收敛后,将训练完成的U-Net用于生成重建测试目标光场的显示图案。训练和测试结果表明,相比基于堆叠CNN和迭代算法的方法,所提出的基于U-Net的压缩光场显示图案生成方法具有重建质量更高、计算资源少的优势。Objective 3D display technology is the entrance to the realistic-feeling metaverse for tabletop,portable,and near-eye electronic devices.True 3D displays are mainly divided into light field displays and holographic displays,among which light field displays can be further subdivided into integral-imaging displays,directional light field displays,and compressive light field displays.Compressive light field displays utilize the scattering characteristic of display panels and the correlation between viewpoint images of the 3D scene.The compressive light field display is a candidate for portable 3D display owing to its compact structure,moderate viewing angle,and high spatial resolution.However,computational resources of portable electronic devices are restricted to satisfy their duration demand.Meanwhile,iterative algorithms to solve the compressive light field display patterns have the problem of heavy computation,preventing compressive light field displays from being a practical solution to portable dynamic 3D displays.With the development of artificial intelligence technology,image generation algorithms based on deep learning are gradually applied to 3D displays.Deep neural networks can be trained to fit the iterative process.Additionally,fast display image synthesis could be realized with rapid forward propagation of artificial neural networks.Previously,researchers proposed a stacked CNN-based method to generate images for compressive light field displays.However,the stacked CNN-based method suffers from convergence and over-fitting problems.U-Net is initially employed for image segmentation in computed tomography to handle slicing data and output the organ’s cancer probability.The skip connection added in the U-Net architecture significantly improves its convergence compared with the stacked CNN model.Light field data are pretty similar to slicing data in computed tomography.Thus,we introduce U-Net as the network model for optimizing compressive light field display patterns for better convergence and generali

关 键 词：物理光学 成像系统 压缩光场显示 光场渲染 深度学习 

分 类 号：TN27[电子电信—物理电子学]