Recovering 3D Structure of Multilayer Transparent Objects from Multi-view Ray Tracing

被引:0
|
作者
Maeda, Atsunori [1 ]
Sakaue, Fumihiko [1 ]
Sato, Jun [1 ]
机构
[1] Nagoya Inst Technol, Dept Comp Sci & Engn, Showa Ku, Nagoya, Aichi 4668555, Japan
来源
PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2017), VOL 6 | 2017年
关键词
Transparent Objects; Ray Tracing; Multilayer; 3D Reconstruction;
D O I
10.5220/0006265905230527
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
3D reconstruction of object shape is one of the most important problems in the field of computer vision. Although many methods have been proposed up to now, the 3D reconstruction of transparent objects is still a very difficult unsolved problem. In particular, if the transparent objects have multiple layers with different refraction properties, the recovery of the 3D structure of transparent objects is quite difficult. In this paper, we propose a method for recovering the 3D structure of multilayer transparent objects. For this objective we introduce a new representation of 3D space by using a boxel with refraction properties, and recovering the refraction properties of each boxel by using the ray tracing. The efficiency of the proposed method is shown by some preliminary experiments.
引用
收藏
页码:523 / 527
页数:5
相关论文
共 50 条
  • [21] Efficient multi-view ray tracing using edge detection and shader reuse
    Andersson, Magnus
    Johnsson, Bjorn
    Munkberg, Jacob
    Clarberg, Petrik
    Hasselgren, Jon
    Akenine-Moller, Tomas
    VISUAL COMPUTER, 2011, 27 (6-8): : 665 - 676
  • [22] Efficient multi-view ray tracing using edge detection and shader reuse
    Magnus Andersson
    Björn Johnsson
    Jacob Munkberg
    Petrik Clarberg
    Jon Hasselgren
    Tomas Akenine-Möller
    The Visual Computer, 2011, 27 : 665 - 676
  • [23] Simultaneous Multi-view Relative Pose Estimation and 3D Reconstruction from Planar Regions
    Frohlich, Robert
    Kato, Zoltan
    COMPUTER VISION - ACCV 2018 WORKSHOPS, 2019, 11367 : 467 - 483
  • [24] Large-Scale 3D Reconstruction from Multi-View Imagery: A Comprehensive Review
    Luo, Haitao
    Zhang, Jinming
    Liu, Xiongfei
    Zhang, Lili
    Liu, Junyi
    REMOTE SENSING, 2024, 16 (05)
  • [25] Cortical Volumetry using 3D Reconstruction of Metacarpal Bone from Multi-view Images
    Jayakar, Avinash D.
    Sambath, Gautham
    Areeckal, Anu Shaju
    David, Sumam S.
    2018 IEEE RECENT ADVANCES IN INTELLIGENT COMPUTATIONAL SYSTEMS (RAICS), 2018, : 79 - 83
  • [26] Study of improved ray tracing parallel algorithm for CGH of 3D objects on GPU
    Cong, Bin
    Jiang, Xiaoyu
    Yao, Jun
    Zhao, Kai
    INTERNATIONAL SYMPOSIUM ON OPTOELECTRONIC TECHNOLOGY AND APPLICATION 2014: ADVANCED DISPLAY TECHNOLOGY; AND NONIMAGING OPTICS: EFFICIENT DESIGN FOR ILLUMINATION AND SOLAR CONCENTRATION, 2014, 9296
  • [27] Adaptive Interaction-Based Multi-view 3D Object Reconstruction
    Miao, Jun
    Zheng, Yilin
    Yan, Jie
    Li, Lei
    Chu, Jun
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT II, 2023, 14255 : 51 - 64
  • [28] Colorful 3D reconstruction at high resolution using multi-view representation
    Zheng, Yanping
    Zeng, Guang
    Li, Haisheng
    Cai, Qiang
    Du, Junping
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2022, 85
  • [29] JOINT MULTI-VIEW FOREGROUND SEGMENTATION AND 3D RECONSTRUCTION WITH TOLERANCE LOOP
    Gallego, Jaime
    Salvador, Jordi
    Casas, Josep R.
    Pardas, Montse
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011, : 997 - 1000
  • [30] Development of multi-view 3D reconstruction system for bubble flow measurement
    Saito, Miki
    Kanai, Taizo
    FLOW MEASUREMENT AND INSTRUMENTATION, 2024, 99