The Making and Breaking of Camouflage

被引:3
作者
Lamdouar, Hala [1 ]
Xie, Weidi [1 ,2 ]
Zisserman, Andrew [1 ]
机构
[1] Univ Oxford, Visual Geometry Grp, Oxford, England
[2] Shanghai Jiao Tong Univ, CMIC, Shanghai, Peoples R China
来源
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV | 2023年
基金
英国工程与自然科学研究理事会; 国家重点研发计划;
关键词
D O I
10.1109/ICCV51070.2023.00083
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Not all camouflages are equally effective, as even a partially visible contour or a slight color difference can make the animal stand out and break its camouflage. In this paper, we address the question of what makes a camouflage successful, by proposing three scores for automatically assessing its effectiveness. In particular, we show that camouflage can be measured by the similarity between background and foreground features and boundary visibility. We use these camouflage scores to assess and compare all available camouflage datasets. We also incorporate the proposed camouflage score into a generative model as an auxiliary loss and show that effective camouflage images or videos can be synthesised in a scalable manner. The generated synthetic dataset is used to train a transformer-based model for segmenting camouflaged animals in videos. Experimentally, we demonstrate state-of-the-art camouflage breaking performance on the public MoCA-Mask benchmark.
引用
收藏
页码:832 / 842
页数:11
相关论文
共 41 条
  • [1] It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos
    Bideau, Pia
    Learned-Miller, Erik
    [J]. COMPUTER VISION - ECCV 2016, PT VIII, 2016, 9912 : 433 - 449
  • [2] Bideau Pia, 2018, P ECCV WORKSH
  • [3] Brox T, 2010, LECT NOTES COMPUT SC, V6315, P282, DOI 10.1007/978-3-642-15555-0_21
  • [4] Masked-attention Mask Transformer for Universal Image Segmentation
    Cheng, Bowen
    Misra, Ishan
    Schwing, Alexander G.
    Kirillov, Alexander
    Girdhar, Rohit
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1280 - 1289
  • [5] Implicit Motion Handling for Video Camouflaged Object Detection
    Cheng, Xuelian
    Xiong, Huan
    Fan, Deng-Ping
    Zhong, Yiran
    Harandi, Mehrtash
    Drummond, Tom
    Ge, Zongyuan
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 13854 - 13863
  • [6] Choudhury Subhabrata, 2022, P BMVC
  • [7] Doan Khoa D, 2020, ARXIV200311774
  • [8] Efros A. A., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1033, DOI 10.1109/ICCV.1999.790383
  • [9] The kinetics of carbon monoxide reduction of magnetite concentrate particles through CFD modelling
    Fan, De-Qiu
    Elzohiery, Mohamed
    Mohassab, Yousef
    Sohn, H. Y.
    [J]. IRONMAKING & STEELMAKING, 2021, 48 (07) : 769 - 778
  • [10] FreAchet Maurice, 1957, CR HEBD ACAD SCI, P689