Light-field generation for 3D light-field display with IARF and adaptive ray sampling

被引:0
|
作者
Yang, Zeyuan [1 ]
Sang, Xinzhu [1 ]
Yan, Binbin [1 ]
Yu, Xunbo [1 ]
Ji, Luyu [1 ]
Yang, Jiahui [1 ]
Li, Jingwen [1 ]
机构
[1] Beijing Univ Posts & Telecommun, State Key Lab Informat Photon & Opt Commun, Beijing 100876, Peoples R China
来源
OPTICS EXPRESS | 2024年 / 32卷 / 27期
基金
中国国家自然科学基金;
关键词
VIEW SYNTHESIS; LENS ARRAY;
D O I
10.1364/OE.546442
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
High-quality light-field generation of real scenes based on view synthesis remains a significant challenge in three-dimensional (3D) light-field displays. Recent advances in neural radiance fields have greatly enhanced light-field generation. However, challenges persist in synthesizing high-quality cylindrical viewpoints within a short time. To handle these issues, the instant adaptive radiance field (IARF) method is proposed to enhance the synthesized light-field quality from a set of captured images. In the ray marching process, the adaptive ray sampling technique is presented for resampling within both discrete occupied grids and continuous unoccupied spaces, which ensures that more representative points are acquired, thereby improving image quality. Furthermore, the volumetric sampling consistency (VSC) loss is used for adaptive ray sampling, which maintains the consistency, contributing to shorter training times with high quality. The iterative network structure of IARF is designed to achieve the resampling of points along emitted rays, which ensures the convergence of the density distributions and enhances synthesis accuracy. The distortion loss is introduced to optimize the unbounded scene geometry, and more realistic rendering is achieved. Finally, the expected viewpoint rendering with a backward ray tracing technique is presented to directly render synthetic images based on off-axis light-field image coding. Experimental results validate the effectiveness of our method. The IARF can achieve more detailed viewpoint generation for 360-degree scenes in a shorter training time. The ablation study demonstrates the validity of the proposed VSC loss and utilized distortion loss. Compared to other established methods, an average improvement of 2.14 dB in PSNR is achieved with approximately 9 minutes of training. The IARF can generate synthetic images at arbitrary positions and viewing angles within the scene, rather than being limited to a narrow field of view. Notably, a smooth motion parallax is obtained based on the 3D light-field display with 7680x4320 resolution over a large viewing angle. We believe that the IARF method can facilitate light-field generation by synthesizing real-world scenes, which represent a promising application for 3D light-field display. (c) 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
引用
收藏
页码:48696 / 48716
页数:21
相关论文
共 50 条
  • [1] 3D touchable holographic light-field display
    Yamaguchi, Masahiro
    Higashida, Ryo
    APPLIED OPTICS, 2016, 55 (03) : A178 - A183
  • [2] Depth reconstruction for 3D light-field display based on axially distributed light field
    Yao, Tong
    Sang, Xinzhu
    Wang, Peng
    Xie, Songlin
    Chen, Duo
    Wang, Huachun
    OPTICAL ENGINEERING, 2021, 60 (05)
  • [3] Real-time light-field generation based on the visual hull for the 3D light-field display with free-viewpoint texture mapping
    Yang, Zeyuan
    Sang, Xinzhu
    Yan, Binbin
    Chen, Duo
    Wang, Peng
    Wan, Huaming
    Chen, Shuo
    Li, Jingwen
    OPTICS EXPRESS, 2023, 31 (02) : 1125 - 1140
  • [4] Hybird Light-field Display
    Kim, Dongyeon
    Lee, Seungjae
    Moon, Seokil
    Lee, Byoungho
    ADVANCES IN DISPLAY TECHNOLOGIES VIII, 2018, 10556
  • [5] Light-field displays and Light-field Optics
    Iwane, Toru
    2016 15TH WORKSHOP ON INFORMATION OPTICS (WIO), 2016,
  • [6] Light-Field Microscopy with a Consumer Light-Field Camera
    Mignard-Debise, Lois
    Ihrke, Ivo
    2015 INTERNATIONAL CONFERENCE ON 3D VISION, 2015, : 335 - 343
  • [7] Portrait relighting for 3D light-field display based on radiance fields
    Shen, Sheng
    Xing, Shujun
    Sang, Xinzhu
    Yan, Binbin
    Zhang, Shuang
    Xie, Xinhui
    Yang, Jiahui
    OPTICS COMMUNICATIONS, 2024, 572
  • [8] Light-field based 3D optical tweezers
    Le Priol, Etienne
    Sasaki, Atsushi
    Beaucamp, Anthony
    EOS ANNUAL MEETING, EOSAM 2024, 2024, 309
  • [9] LIGHT-FIELD GENERATION BY SEVERAL SCREEN TYPES FOR GLASSES-FREE TABLETOP 3D DISPLAY
    Yoshida, Shunsuke
    Kawakita, Masahiro
    Ando, Hiroshi
    2011 3DTV CONFERENCE: THE TRUE VISION - CAPTURE, TRANSMISSION AND DISPLAY OF 3D VIDEO (3DTV-CON), 2011,
  • [10] Optimizing depth of field in 3D light-field display by analyzing and controlling light-beam divergence angle
    Yu, Xunbo
    Wang, Yiping
    Gao, Xin
    Li, Hanyu
    Liu, Kexin
    Yan, Binbin
    Sang, Xinzhu
    CHINESE OPTICS LETTERS, 2024, 22 (01)