Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data

被引：0
|
作者：
Kulkarni, Nilesh [1 ]
Jin, Linyi [1 ]
Johnson, Justin [1 ]
Fouhey, David F. [1 ]
机构：
[1] Univ Michigan, Ann Arbor, MI 48109 USA
来源：
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2023年
关键词：
D O I：
10.1109/CVPR52729.2023.01655
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We introduce a method that can learn to predict scene-level implicit functions for 3D reconstruction from posed RGBD data. At test time, our system maps a previously unseen RGB image to a 3D reconstruction of a scene via implicit functions. While implicit functions for 3D reconstruction have often been tied to meshes, we show that we can train one using only a set of posed RGBD images. This setting may help 3D reconstruction unlock the sea of accelerometer+RGBD data that is coming with new phones. Our system, D2-DRDF, can match and sometimes outperform current methods that use mesh supervision and shows better robustness to sparse data.
引用
收藏
页码：17256 / 17265
页数：10
相关论文
共 50 条
  • [41] Collaboration on scene graph based 3D data
    Ammon, Lorenz
    Bieri, Hanspeter
    GRAPP 2006: PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON COMPUTER GRAPHICS THEORY AND APPLICATIONS, 2006, : 259 - +
  • [42] Deep Learning for 3D Scene Reconstruction and Segmentation from Stereo Images
    Kniaz, Vladimir V.
    Knyaz, Vladimir A.
    Ippolitov, Evgeny, V
    Novikov, Mikhail M.
    Grodzistky, Lev
    Moshkantsev, Petr
    MULTIMODAL SENSING AND ARTIFICIAL INTELLIGENCE: TECHNOLOGIES AND APPLICATIONS II, 2021, 11785
  • [43] Learning from 3D (Point Cloud) Data
    Hsu, Winston H.
    PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 2697 - 2698
  • [44] Learning 3D Scene Semantics and Structure from a Single Depth Image
    Yang, Bo
    Lai, Zihang
    Lu, Xiaoxuan
    Lin, Shuyu
    Wen, Hongkai
    Markham, Andrew
    Trigoni, Niki
    PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 422 - 425
  • [45] Implicit-Explicit Coupling Enhancement for UAV Scene 3D Reconstruction
    Lin, Xiaobo
    Xu, Shibiao
    APPLIED SCIENCES-BASEL, 2024, 14 (06):
  • [46] Localized scene interpretation from 3D models, range, and optical data
    Stevens, MR
    Beveridge, JR
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2000, 80 (02) : 111 - 129
  • [47] RedNavi: Building a 3D Scene of the Current Sea from AIS Data
    Liu, Hongze
    Wakabayashi, Nobukazu
    SUSTAINABILITY, 2022, 14 (19)
  • [48] Simplification of Moving 3D Scene Data on GPU
    Chenchu, Rajesh
    Michiels, Nick
    Rogmans, Sammy
    Bekaert, Philippe
    SIGMAP: PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON E-BUSINESS AND TELECOMMUNICATIONS - VOL. 5, 2016, : 95 - 98
  • [49] Collaboration on scene graph based 3D data
    Ammon, Lorenz
    Bieri, Hanspeter
    ADVANCES IN COMPUTER GRAPHICS AND COMPUTER VISION, 2007, 4 : 78 - 90
  • [50] Stencil-based 3D facial relief creation from RGBD images for 3D printing
    Jung, Soonchul
    Choi, Yoon-Seok
    Kim, Jin-Seo
    ETRI JOURNAL, 2020, 42 (02) : 272 - 281
12345