Context-aware Patch-based Method for Facade Inpainting

被引:1
|
作者
Kottler, Benedikt [1 ]
Bulatov, Dimitri [1 ]
Zhang Xingzi [2 ]
机构
[1] Fraunhofer Inst Optron Syst Technol & Image Explo, Dept Scene Anal, D-76275 Ettlingen, Germany
[2] Fraunhofer Singapore, Singapore, Singapore
关键词
City Modeling; Inpainting; Patch-based Inpainting; Textures; Texture Image; Facade Elements;
D O I
10.5220/0008874802100218
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Realistic representations of 3D urban scenes is an important aspect of scene understanding and has many applications. Given untextured polyhedral Level-of-Detail 2 (LoD2) models of building and imaging containing facade textures, occlusions caused by foreground objects are an essential disturbing factor of fac<comma>ade textures. We developed a modification of a well-known patch-based inpainting method and used the knowledge about facade details in order to improve the facade inpainting of occlusions. Our modification focuses on suppression of undesired, superfluous repetitions of textures. To achieve this, a coarse inpainting result by a structural-based method is used to influence the choice of the best patch so that homogeneous regions are preferred. The coarse inpainting is calculated using the context knowledge and average color instead of traditionally applied arbitrary structural inpainting. Our modification furthermore introduces a parameter that allows to weight the influence of the coarse inpainting. A parameter study shows that this parameter can be chosen intuitively and does not require any parameter choice method. The cleaned facade textures could be successfully integrated into the accordingly adjusted building models thus upgrading them to LoD3.
引用
收藏
页码:210 / 218
页数:9
相关论文
共 50 条
  • [1] Texture and color descriptors as a tool for context-aware patch-based image inpainting
    Ruzic, Tijana
    Pizurica, Aleksandra
    [J]. IMAGE PROCESSING: ALGORITHMS AND SYSTEMS X AND PARALLEL PROCESSING FOR IMAGING APPLICATIONS II, 2012, 8295
  • [2] Context-Aware Patch-Based Image Inpainting Using Markov Random Field Modeling
    Ruzic, Tijana
    Pizurica, Aleksandra
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (01) : 444 - 456
  • [3] Context-Aware Semantic Inpainting
    Li, Haofeng
    Li, Guanbin
    Lin, Liang
    Yu, Hongchuan
    Yu, Yizhou
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2019, 49 (12) : 4398 - 4411
  • [4] Radiometric confidence criterion for patch-based inpainting
    Fayer, Julien
    Morin, Geraldine
    Gasparini, Simone
    Daisy, Maxime
    Coudrin, Benjamin
    [J]. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 2723 - 2728
  • [5] A Decoupled method for image inpainting with patch-based low rank regulariztion
    Li, Fang
    Lv, Xiaoguang
    [J]. APPLIED MATHEMATICS AND COMPUTATION, 2017, 314 : 334 - 348
  • [6] Context-Aware Image Inpainting with Learned Semantic Priors
    Zhang, Wendong
    Zhu, Junwei
    Tai, Ying
    Wang, Yunbo
    Chu, Wenqing
    Ni, Bingbing
    Wang, Chengjie
    Yang, Xiaokang
    [J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 1323 - 1329
  • [7] FACADE - A framework for context-aware content adaptation and delivery
    Kurz, B
    Popescu, I
    Gallacher, S
    [J]. SECOND ANNUAL CONFERENCE ON COMMUNICATION NETWORKS AND SERVICES RESEARCH, PROCEEDINGS, 2004, : 46 - 55
  • [8] MARKOV RANDOM FIELD BASED IMAGE INPAINTING WITH CONTEXT-AWARE LABEL SELECTION
    Ruzic, Tijana
    Pizurica, Aleksandra
    Philips, Wilfried
    [J]. 2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012), 2012, : 1733 - 1736
  • [9] ADAPTIVE PATCH-BASED INPAINTING FOR IMAGE BLOCK RECOVERY
    Liu, Yunqiang
    Wang, Jin
    Zhang, Huanhuan
    [J]. VISAPP 2010: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 1, 2010, : 52 - 59
  • [10] Iterative Gradient-Driven Patch-Based Inpainting
    Tae-o-sot, Sarawut
    Nishihara, Akinori
    [J]. ADVANCES IN IMAGE AND VIDEO TECHNOLOGY, PT II, 2011, 7088 : 71 - +