Counterfactual Depth from a Single RGB Image

被引:2
|
作者
Issaranon, Theerasit [1 ]
Zou, Chuhang [1 ]
Forsyth, David [1 ]
机构
[1] Univ Illinois, Urbana, IL 61801 USA
关键词
D O I
10.1109/ICCVW.2019.00268
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We describe a method that predicts, from a single RGB image, a depth map that describes the scene when a masked object is removed - we call this "counterfactual depth" that models hidden scene geometry together with the observations. Our method works for the same reason that scene completion works: the spatial structure of objects is simple. But we offer a much higher resolution representation of space than current scene completion methods, as we operate at pixel-level precision and do not rely on a voxel representation. Furthermore, we do not require RGBD inputs. Our method uses a standard encoder-decoder architecture, and with a decoder modified to accept an object mask. We describe a small evaluation dataset that we have collected, which allows inference about what factors affect reconstruction most strongly. Using this dataset, we show that our depth predictions for masked objects are better than other baselines.
引用
收藏
页码:2129 / 2138
页数:10
相关论文
共 50 条
  • [21] Semantic Reconstruction based on RGB Image and Sparse Depth
    Cai, Yu
    Ding, Yinzhang
    Li, Dongxiao
    Zhang, Ming
    [J]. TWELFTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2020), 2021, 11720
  • [22] Repairing IR depth image with 2D RGB image
    Yu, Yeh-Wei
    Wang, Tzu-Kai
    Lau, Chi-Chung
    Wang, Jia-Ching
    Yang, Tsung-Hsun
    Chern, Jann-Long
    Sun, Ching-Cherng
    [J]. CURRENT DEVELOPMENTS IN LENS DESIGN AND OPTICAL ENGINEERING XIX, 2018, 10745
  • [23] EFFICIENT DEPTH ESTIMATION FROM SINGLE IMAGE
    Zhou, Wei
    Dai, Yuchao
    He, Renjie
    [J]. 2014 IEEE CHINA SUMMIT & INTERNATIONAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (CHINASIP), 2014, : 296 - 300
  • [24] Fast depth extraction from a single image
    He, Lei
    Dong, Qiulei
    Wang, Guanghui
    [J]. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2016, 13 : 1 - 11
  • [25] CHESS RECOGNITION FROM A SINGLE DEPTH IMAGE
    Wei, Yu-An
    Huang, Tzu-Wei
    Chen, Hwann-Tzong
    Liu, JenChi
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2017, : 931 - 936
  • [26] DEPTH FROM DEFOCUS AND BLUR FOR SINGLE IMAGE
    Sun, Huadong
    Zhao, Zhijie
    Jin, Xuesong
    Niu, Lianding
    Zhang, Lizhi
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP 2013), 2013,
  • [27] Omnidirectional depth computation from a single image
    Orghidan, R
    Mouaddib, EM
    Salvi, J
    [J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-4, 2005, : 1222 - 1227
  • [28] Data Fusion of RGB and Depth Data with Image Enhancement
    Wunsch, Lennard
    Tenorio, Christian Goerner
    Anding, Katharina
    Golomoz, Andrei
    Notni, Gunther
    [J]. JOURNAL OF IMAGING, 2024, 10 (03)
  • [29] Scene Intrinsics and Depth from a Single Image
    Shelhamer, Evan
    Barron, Jonathan T.
    Darrell, Trevor
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW), 2015, : 235 - 242
  • [30] On the Recovery of Depth from a Single Defocused Image
    Zhuo, Shaojie
    Sim, Terence
    [J]. COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS, 2009, 5702 : 889 - 897