Multi-View Image-Based 3D Reconstruction in Indoor Scenes:A Survey

被引:0
作者
LU Ping [1 ,2 ]
SHI Wenzhe [1 ,2 ]
QIAO Xiuquan [3 ]
机构
[1] State Key Laboratory of Mobile Network and Mobile Multimedia Technology
[2] ZTE Corporation
[3] State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and
关键词
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
Three-dimensional reconstruction technology plays an important role in indoor scenes by converting objects and structures in indoor environments into accurate 3D models using multi-view RGB images. It offers a wide range of applications in fields such as virtual reality, aug-mented reality, indoor navigation, and game development. Existing methods based on multi-view RGB images have made significant progress in 3D reconstruction. These image-based reconstruction methods not only possess good expressive power and generalization performance, but also handle complex geometric shapes and textures effectively. Despite facing challenges such as lighting variations, occlusion, and texture loss in in-door scenes, these challenges can be effectively addressed through deep neural networks, neural implicit surface representations, and other tech-niques. The technology of indoor 3D reconstruction based on multi-view RGB images has a promising future. It not only provides immersive and interactive virtual experiences but also brings convenience and innovation to indoor navigation, interior design, and virtual tours. As the technol-ogy evolves, these image-based reconstruction methods will be further improved to provide higher quality and more accurate solutions to indoor scene reconstruction.
引用
收藏
页码:91 / 98
页数:8
相关论文
共 9 条
  • [1] Scene Visual Perception and AR Navigation Applications
    LU Ping
    SHENG Bin
    SHI Wenzhe
    [J]. ZTE Communications, 2023, 21 (01) : 81 - 88
  • [2] xAtlas: scalable small variant calling across heterogeneous next-generation sequencing experiments..[J].Farek Jesse;Hughes Daniel;Salerno William;Zhu Yiming;Pisupati Aishwarya;Mansfield Adam;Krasheninina Olga;English Adam C;Metcalf Ginger;Boerwinkle Eric;Muzny Donna M;Gibbs Richard;Khan Ziad;Sedlazeck Fritz J.GigaScience.2022,
  • [3] ColMap: A memory-efficient occupancy grid mapping framework.[J].Fisher Alex;Cannizzaro Ricardo;Cochrane Madeleine;Nagahawatte Chatura;Palmer Jennifer L..Robotics and Autonomous Systems.2021, prepublish
  • [4] Cost volume pyramid based depth inference for multi-view stereo.[J].Yang J.;Mao W.;Alvarez J.M.;Liu M..Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2020,
  • [5] Wider or Deeper: Revisiting the ResNet Model for Visual Recognition.[J].Zifeng Wu;Chunhua Shen;Anton van den Hengel.Pattern Recognition.2019,
  • [6] DPSNet: End-to-end Deep Plane Sweep Stereo..[J].Sunghoon Im;Hae-Gon Jeon;Stephen Lin;In So Kweon.CoRR.2019,
  • [7] Speeded-Up Robust Features (SURF).[J].Herbert Bay;Andreas Ess;Tinne Tuytelaars;Luc Van Gool.Computer Vision and Image Understanding.2007, 3
  • [8] SIFT: predicting amino acid changes that affect protein function
    Ng, PC
    Henikoff, S
    [J]. NUCLEIC ACIDS RESEARCH, 2003, 31 (13) : 3812 - 3814
  • [9] Marching cubes: A high resolution 3D surface construction algorithm.[J].William E. Lorensen;Harvey E. Cline.ACM SIGGRAPH Computer Graphics.1987, 4