基于 3D 光场显示的内容合成技术研究

[1] 吴金建. 基于人类视觉系统的图像信息感知和图像质量评价[J]. 西安: 西安电子科技大学, 2014.
[2] LAWRENCE J, GOLDMAN D B, ACHAR S, et al. Project Starline: A high-fidelity telepres￾ence system[Z]. 2021.
[3] 万文强. 基于衍射光学的裸眼 3D 显示研究[D]. 苏州: 苏州大学, 2018.
[4] KIM N, PHAN A H, ERDENEBAT M U, et al. 3D display technology[J]. Disp. Imag, 2014, 1(1): 73-95.
[5] WETZSTEIN G, LANMAN D, HEIDRICH W, et al. Layered 3D: tomographic image synthesisfor attenuation-based light field and high dynamic range displays[M]//ACM SIGGRAPH 2011papers. 2011: 1-12.
[6] SON J Y, JAVIDI B, KWACK K D. Methods for displaying three-dimensional images[J].Proceedings of the IEEE, 2006, 94(3): 502-523.
[7] VIENNE C, SORIN L, BLONDÉ L, et al. Effect of the accommodation-vergence conflict onvergence eye movements[J]. Vision research, 2014, 100: 124-133.
[8] FAVALORA G E, DORVAL R K, HALL D M, et al. Volumetric three-dimensional displaysystem with rasterization hardware[C]//Stereoscopic Displays and Virtual Reality Systems VIII:Vol. 4297. SPIE, 2001: 227-235.
[9] 李春锦. 基于双目立体视觉 3D 显示检测系统的研究[D]. 浙江大学, 2016.
[10] WETZSTEIN G, LANMAN D, HEIDRICH W, et al. Layered 3D: tomographic image synthe￾sis for attenuation-based light field and high dynamic range displays[C/OL]//SIGGRAPH ’11:ACM SIGGRAPH 2011 Papers. New York, NY, USA: Association for Computing Machinery,2011. https://doi.org/10.1145/1964921.1964990.
[11] WETZSTEIN G, LANMAN D, HIRSCH M, et al. Tensor displays: compressive light fieldsynthesis using multilayer displays with directional backlighting[J/OL]. ACM Trans. Graph.,2012, 31(4). https://doi.org/10.1145/2185520.2185576.
[12] JONES A, NAGANO K, LIU J, et al. Interpolating vertical parallax for an autostereoscopicthree-dimensional projector array[J]. Journal of Electronic Imaging, 2014, 23(1): 011005-011005.
[13] SOKOLOV A. Autostereoscopy and integral photography by Professor Lippmann’s method[J].Izd. MGU, 1911.
[14] SANG X, GAO X, YU X, et al. Interactive floating full-parallax digital three-dimensional light￾field display based on wavefront recomposing[J]. Optics express, 2018, 26(7): 8883-8889.
[15] XIA Y P, XING Y, REN H, et al. Integral imaging tabletop 3D display system based on com￾pound lens array[C]//VR/AR and 3D Displays: First International Conference, ICVRD 2020,Hangzhou, China, December 20, 2020, Revised Selected Papers 1. Springer, 2021: 14-20.
[16] 马群刚. 3D 显示技术[M]. 电子工业出版社, 2020.
[17] FATTAL D, PENG Z, TRAN T, et al. A multi-directional backlight for a wide-angle, glasses￾free three-dimensional display[J]. Nature, 2013, 495(7441): 348-351.
[18] KREBS P, LIANG H, FAN H, et al. Homogeneous free-form directional backlight for 3Ddisplay[J]. Optics Communications, 2017, 397: 112-117.
[19] ZHAO J, DING Y, DAI Z, et al. Viewing Zone Expansion of Autostereoscopic Display WithComposite Lenticular Lens Array and Saddle Lens Array[J/OL]. IEEE Photonics Journal, 2023,15(4): 1-6. DOI: 10.1109/JPHOT.2023.3301559.
[20] 韩冬雪. 多视点裸眼 3D 电视的虚拟视点生成方法研究[D]. 山东大学, 2019.
[21] ROGMANS S, LU J, BEKAERT P, et al. Real-time stereo-based view synthesis algorithms:A unified framework and evaluation on commodity GPUs[J/OL]. Signal Processing: ImageCommunication, 2009, 24(1): 49-64. https://www.sciencedirect.com/science/article/pii/S0923596508001124. DOI: https://doi.org/10.1016/j.image.2008.10.005.
[22] MILDENHALL B, SRINIVASAN P P, ORTIZ-CAYON R, et al. Local light field fusion: Prac￾tical view synthesis with prescriptive sampling guidelines[J]. ACM Transactions on Graphics(TOG), 2019, 38(4): 1-14.
[23] NIKLAUS S, MAI L, YANG J, et al. 3d ken burns effect from a single image[J]. ACM Trans￾actions on Graphics (ToG), 2019, 38(6): 1-15.
[24] SHIH M L, SU S Y, KOPF J, et al. 3d photography using context-aware layered depth inpainting[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020: 8028-8038.
[25] MILDENHALL B, SRINIVASAN P P, TANCIK M, et al. Nerf: Representing scenes as neuralradiance fields for view synthesis[J]. Communications of the ACM, 2021, 65(1): 99-106.
[26] GARBIN S J, KOWALSKI M, JOHNSON M, et al. Fastnerf: High-fidelity neural rendering at200fps[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021:14346-14355.
[27] DENG K, LIU A, ZHU J Y, et al. Depth-supervised nerf: Fewer views and faster training for free[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022: 12882-12891.
[28] SUHAIL M, ESTEVES C, SIGAL L, et al. Light field neural rendering[C]//Proceedings of theIEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 8269-8279.
[29] TIAN F, DU S, DUAN Y. Mononerf: Learning a generalizable dynamic radiance field frommonocular videos[C]//Proceedings of the IEEE/CVF International Conference on ComputerVision. 2023: 17903-17913.
[30] XIONG Z L, LI S L, CHEN J, et al. Nonunified integral imaging elemental image array gener￾ation method based on selective pixel sampling algorithm[J]. Applied optics (2004), 2015, 54(9): 2532-2536.
[31] SYED I A, DATAR M, PATKAR S. Accelerated Stereo Vision Using Nvidia Jetson and IntelAVX[C]//Computer Vision and Image Processing: 5th International Conference, CVIP 2020,Prayagraj, India, December 4-6, 2020, Revised Selected Papers, Part II 5. Springer, 2021: 137-148.
[32] XING S, SANG X, CAO L, et al. High-speed integral image object-order rendering method based on reverse perspective technique and optical reconstruction[J/OL]. Optik, 2020, 202:163025. https://www.sciencedirect.com/science/article/pii/S0030402619309027. DOI: https://doi.org/10.1016/j.ijleo.2019.163025.
[33] REN H, WANG Q H, XING Y, et al. Super-multiview integral imaging scheme based on sparsecamera array and CNN super-resolution[J/OL]. Appl. Opt., 2019, 58(5): A190-A196. https://opg.optica.org/ao/abstract.cfm?URI=ao-58-5-A190. DOI: 10.1364/AO.58.00A190.
[34] 申瑞瑶. 并行随机渐进式光子映射算法在快速光场渲染中的应用[D]. 北京邮电大学.
[35] YU X, LI H, SANG X, et al. Aberration correction based on a pre-correction convolutionalneural network for light-field displays[J/OL]. Opt. Express, 2021, 29(7): 11009-11020. https://opg.optica.org/oe/abstract.cfm?URI=oe-29-7-11009. DOI: 10.1364/OE.419570.
[36] CAO S, MA H, LI C, et al. Dual convolutional neural network for aberration pre-correctionand image quality enhancement in integral imaging display[J/OL]. Opt. Express, 2023, 31(21):34609-34625. https://opg.optica.org/oe/abstract.cfm?URI=oe-31-21-34609. DOI: 10.1364/OE.501909.
[37] ZHAO W X, WANG Q H, WANG A H, et al. Autostereoscopic display based on two-layerlenticular lenses[J]. Optics letters, 2010, 35(24): 4127-4129.
[38] WANG Y, LI M, SURMAN P, et al. A Low-cost Eye-tracking Autostereoscopic Three dimensional Display System[C]//2021 Photonics & Electromagnetics Research Symposium(PIERS). IEEE, 2021: 391-395.
[39] SURMAN P, ZHENG C, ZHANG C, et al. Determining depth of field for slanted lenticular 3Ddisplays[J]. Optics Continuum, 2023, 2(9): 1929-1940.
[40] 李剑. 基于双目相机的虚拟视点实时绘制系统研究[D]. 哈尔滨工业大学, 2020.
[41] FEHN C. Depth-image-based rendering (DIBR), compression, and transmission for a newapproach on 3D-TV[C]//Stereoscopic displays and virtual reality systems XI: Vol. 5291. SPIE,2004: 93-104.
[42] WAN W, WANG J, ZHANG Y, et al. A comprehensive survey on robust image watermarking[J]. Neurocomputing, 2022, 488: 226-247.
[43] OVERES J. Occlusion filling in depth-image-based rendering[Z]. 2009.
[44] TELEA A. An image inpainting technique based on the fast marching method[J]. Journal ofgraphics tools, 2004, 9(1): 23-34.
[45] AKENINE-MOLLER T, HAINES E, HOFFMAN N. Real-time rendering[M]. AK Peters/crcPress, 2019.
[46] LAINE S, KARRAS T. Efficient sparse voxel octrees[C]//Proceedings of the 2010 ACM SIG GRAPH symposium on Interactive 3D Graphics and Games. 2010: 55-63.