Semantic modeling of indoor scenes with support inference from a single photograph

被引:2
|
作者
Nie, Yinyu [1 ]
Chang, Jian [1 ]
Chaudhry, Ehtzaz [1 ]
Guo, Shihui [2 ]
Smart, Andi [3 ]
Zhang, Jian Jun [1 ]
机构
[1] Bournemouth Univ, Natl Ctr Comp Animat, Poole BH12 5BB, Dorset, England
[2] Xiamen Univ, Sch Software, Xiamen, Peoples R China
[3] Univ Exeter, Ctr Innovat & Serv Res, Sch Business, Exeter, Devon, England
基金
中国国家自然科学基金;
关键词
fully convolutional network; indoor scene reconstruction; semantic modeling; support inference;
D O I
10.1002/cav.1825
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
We present an automatic approach for the semantic modeling of indoor scenes based on a single photograph, instead of relying on depth sensors. Without using handcrafted features, we guide indoor scene modeling with feature maps extracted by fully convolutional networks. Three parallel fully convolutional networks are adopted to generate object instance masks, a depth map, and an edge map of the room layout. Based on these high-level features, support relationships between indoor objects can be efficiently inferred in a data-driven manner. Constrained by the support context, a global-to-local model matching strategy is followed to retrieve the whole indoor scene. We demonstrate that the proposed method can efficiently retrieve indoor objects including situations where the objects are badly occluded. This approach enables efficient semantic-based scene editing.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] An Interactive Approach to Semantic Modeling of Indoor Scenes with an RGBD Camera
    Shao, Tianjia
    Xu, Weiwei
    Zhou, Kun
    Wang, Jingdong
    Li, Dongping
    Guo, Baining
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2012, 31 (06):
  • [2] Hierarchy-associated semantic-rule inference framework for classifying indoor scenes
    Yu, Dan
    Liu, Peng
    Ye, Zhipeng
    Tang, Xianglong
    Zhao, Wei
    [J]. JOURNAL OF ELECTRONIC IMAGING, 2016, 25 (02)
  • [3] Modeling of Clouds from a Single Photograph
    Dobashi, Yoshinori
    Shinzo, Yusuke
    Yamamoto, Tsuyoshi
    [J]. COMPUTER GRAPHICS FORUM, 2010, 29 (07) : 2083 - 2090
  • [4] Indoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference
    Zhuo, Wei
    Salzmann, Mathieu
    He, Xuming
    Liu, Miaomiao
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 6269 - 6275
  • [5] Geometry Driven Semantic Labeling of Indoor Scenes
    Khan, Salman Hameed
    Bennamoun, Mohammed
    Sohel, Ferdous
    Togneri, Roberto
    [J]. COMPUTER VISION - ECCV 2014, PT I, 2014, 8689 : 679 - 694
  • [6] Automatic Annotation for Semantic Segmentation in Indoor Scenes
    Reza, Md Alimoor
    Naik, Akshay U.
    Chen, Kai
    Crandall, David J.
    [J]. 2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 4970 - 4976
  • [7] Image semantic segmentation of indoor scenes: A survey
    Velastegui, Ronny
    Tatarchenko, Maxim
    Karaoglu, Sezer
    Gevers, Theo
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2024, 248
  • [8] Indoor scene modeling from a single image using normal inference and edge features
    Liu, Mingming
    Guo, Yanwen
    Wang, Jun
    [J]. VISUAL COMPUTER, 2017, 33 (10): : 1227 - 1240
  • [9] Indoor scene modeling from a single image using normal inference and edge features
    Mingming Liu
    Yanwen Guo
    Jun Wang
    [J]. The Visual Computer, 2017, 33 : 1227 - 1240
  • [10] Indoor Segmentation and Support Inference from RGBD Images
    Silberman, Nathan
    Hoiem, Derek
    Kohli, Pushmeet
    Fergus, Rob
    [J]. COMPUTER VISION - ECCV 2012, PT V, 2012, 7576 : 746 - 760