Scene Carving: Scene Consistent Image Retargeting

被引:0
|
作者
Mansfield, Alex [1 ]
Gehler, Peter [1 ]
Van Gool, Luc [1 ,2 ]
Rother, Carsten [3 ]
机构
[1] ETH, Comp Vis Lab, Zurich, Switzerland
[2] Katholieke Univ Leuven, ESAT PSI, Leuven, Belgium
[3] Microsoft Res Ltd, Cambridge, England
来源
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
Image retargeting algorithms often create visually disturbing distortion. We introduce the property of scene consistency, which is held by images which contain no object distortion and have the correct object depth ordering. We present two new image retargeting algorithms that preserve scene consistency. These algorithms make use of a user-provided relative depth map, which can be created easily using a simple GrabCut-style interface. Our algorithms generalize seam carving. We decompose the image retargeting procedure into (a) removing image content with minimal distortion and (b) re-arrangement of known objects within the scene to maximize their visibility. Our algorithms optimize objectives (a) and. (b) jointly. However, they differ considerably in how they achieve tins. We discuss this in detail and present examples illustrating the rationale of preserving scene consistency in retargeting.
引用
收藏
页码:143 / +
页数:2
相关论文
共 50 条
  • [31] Consistent Scene Graph Generation by Constraint Optimization
    Chen, Boqi
    Marussy, Kristof
    Pilarski, Sebastian
    Semerath, Oszkar
    Varro, Daniel
    PROCEEDINGS OF THE 37TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING, ASE 2022, 2022,
  • [32] Semantic embedding: scene image classification using scene-specific objects
    Mohammad Javad Parseh
    Mohammad Rahmanimanesh
    Parviz Keshavarzi
    Zohreh Azimifar
    Multimedia Systems, 2023, 29 : 669 - 691
  • [33] A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection
    Gu, Yating
    Wang, Yantian
    Li, Yansheng
    APPLIED SCIENCES-BASEL, 2019, 9 (10):
  • [34] Semantic embedding: scene image classification using scene-specific objects
    Parseh, Mohammad Javad
    Rahmanimanesh, Mohammad
    Keshavarzi, Parviz
    Azimifar, Zohreh
    MULTIMEDIA SYSTEMS, 2023, 29 (02) : 669 - 691
  • [35] Seam Segment Carving: Retargeting Images to Irregularly-Shaped Image Domains
    Qi, Shaoyu
    Ho, Jeffrey
    COMPUTER VISION - ECCV 2012, PT VI, 2012, 7577 : 314 - 326
  • [36] Distortion-aware image retargeting based on continuous seam carving model
    Cui, Jia
    Cai, Qianqian
    Lu, Hongju
    Jia, Zhenlin
    Tang, Mingxi
    SIGNAL PROCESSING, 2020, 166
  • [37] CONSISTENT AND MULTI-SCALE SCENE GRAPH TRANSFORMER FOR SEMANTIC-GUIDED IMAGE OUTPAINTING
    Yang, Chiao-An
    Wu, Meng-Lin
    Yeh, Raymond A.
    Wang, Yu-Chiang Frank
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 176 - 180
  • [38] Nighttime road scene image enhancement based on cycle-consistent generative adversarial network
    Jia, Yanfei
    Yu, Wenshuo
    Chen, Guangda
    Zhao, Liquan
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [39] Adaptive image retargeting using saliency-based continuous seam carving
    Liu, Zhi
    Yan, Hongbo
    Ngan, King Ngi
    Zhang, Zhaoyang
    OPTICAL ENGINEERING, 2010, 49 (01)
  • [40] Improved seam carving combining with 3D saliency for image retargeting
    Chen, Yanxiang
    Pan, Yifei
    Song, Minglong
    Wang, Meng
    NEUROCOMPUTING, 2015, 151 : 645 - 653