Panoptic 3D Scene Reconstruction From a Single RGB Image

被引:0
|
作者
Dahnert, Manuel [1 ]
Hou, Ji [1 ]
Niessner, Matthias [1 ]
Dai, Angela [1 ]
机构
[1] Tech Univ Munich, Munich, Germany
基金
欧洲研究理事会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Understanding 3D scenes from a single image is fundamental to a wide variety of tasks, such as for robotics, motion planning, or augmented reality. Existing works in 3D perception from a single RGB image tend to focus on geometric reconstruction only, or geometric reconstruction with semantic segmentation or instance segmentation. Inspired by 2D panoptic segmentation, we propose to unify the tasks of geometric reconstruction, 3D semantic segmentation, and 3D instance segmentation into the task of panoptic 3D scene reconstruction - from a single RGB image, predicting the complete geometric reconstruction of the scene in the camera frustum of the image, along with semantic and instance segmentations. We thus propose a new approach for holistic 3D scene understanding from a single RGB image which learns to lift and propagate 2D features from an input image to a 3D volumetric scene representation. We demonstrate that this holistic view of joint scene reconstruction, semantic, and instance segmentation is beneficial over treating the tasks independently, thus outperforming alternative approaches.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
    Huang, Siyuan
    Qi, Siyuan
    Zhu, Yixin
    Xiao, Yinxue
    Xu, Yuanlu
    Zhu, Song-Chun
    [J]. COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 : 194 - 211
  • [2] 3D SCENE RECONSTRUCTION FROM RGB IMAGES
    Rotaru, Razvan-Paul
    Gradinaru, Alexandru
    Moldoveanu, Florica
    [J]. UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE, 2024, 86 (02): : 101 - 112
  • [3] Dense 3D Face Reconstruction from a Single RGB Image
    Mao, Jianxu
    Zhang, Yifeng
    Liu, Caiping
    Tao, Ziming
    Yi, Junfei
    Wang, Yaonan
    [J]. 2022 IEEE 25TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING, CSE, 2022, : 24 - 31
  • [4] 3D-Scene-Former: 3D scene generation from a single RGB image using Transformers
    Chatterjee, Jit
    Vega, Maria Torres
    [J]. VISUAL COMPUTER, 2024,
  • [5] A 3D Reconstruction System for Large Scene Based on RGB-D Image
    Wang, Hongren
    Wang, Pengbo
    Wang, Xiaodi
    Peng, Tianchen
    Zhang, Baochang
    [J]. INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING, 2018, 11266 : 518 - 527
  • [6] BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Image
    Chu, Tao
    Zhang, Pan
    Liu, Qiong
    Wang, Jiaqi
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 4937 - 4946
  • [7] Stage-Based 3D Scene Reconstruction from Single Image
    Liu, Yixian
    Hao, Pengwei
    Izquierdo, Ebroul
    [J]. 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 1034 - 1037
  • [8] Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction
    Zhang, Xiang
    Chen, Zeyuan
    Wei, Fangyin
    Tu, Zhuowen
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 9222 - 9232
  • [9] UV-based reconstruction of 3D garments from a single RGB image
    Rial-Farras, Albert
    Madadi, Meysam
    Escalera, Sergio
    [J]. 2021 16TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2021), 2021,
  • [10] RGB-to-TSDF: Direct TSDF Prediction from a Single RGB Image for Dense 3D Reconstruction
    Kim, Hanjun
    Moon, Jiyoun
    Lee, Beomhee
    [J]. 2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 6714 - 6720