Toward Realistic Image Compositing with Adversarial Learning

被引:43
|
作者
Chen, Bor-Chun [1 ]
Kae, Andrew [2 ]
机构
[1] Univ Maryland, College Pk, MD 20742 USA
[2] Verizon Media Grp, Boston, MA USA
来源
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) | 2019年
关键词
D O I
10.1109/CVPR.2019.00861
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Compositing a realistic image is a challenging task and usually requires considerable human supervision using professional image editing software. In this work we propose a generative adversarial network (GAN) architecture for automatic image compositing. The proposed model consists of four sub-networks: a transformation network that improves the geometric and color consistency of the composite image, a refinement network that polishes the boundary of the composite image, and a pair of discriminator network and a segmentation network for adversarial learning. Experimental results on both synthesized images and real images show that our model, Geometrically and Color Consistent GANs (GCC-GANs), can automatically generate realistic composite images compared to several state-of-the-art methods, and does not require any manual effort.
引用
收藏
页码:8407 / 8416
页数:10
相关论文
共 50 条
  • [21] Realistic River Image Synthesis Using Deep Generative Adversarial Networks
    Gautam, Akshat
    Sit, Muhammed
    Demir, Ibrahim
    FRONTIERS IN WATER, 2022, 4
  • [22] DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis
    Ngxande, Mkhuseli
    Tapamo, Jules-Raymond
    Burke, Michael
    2019 SOUTHERN AFRICAN UNIVERSITIES POWER ENGINEERING CONFERENCE/ROBOTICS AND MECHATRONICS/PATTERN RECOGNITION ASSOCIATION OF SOUTH AFRICA (SAUPEC/ROBMECH/PRASA), 2019, : 111 - 116
  • [23] Order independent image compositing
    Bielski, C
    Soille, P
    IMAGE ANALYSIS AND PROCESSING - ICIAP 2005, PROCEEDINGS, 2005, 3617 : 1076 - 1083
  • [24] Towards realistic image via function learning
    Zareapoor, Masoumeh
    Zhang, Junhao
    Yang, Jie
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (20) : 29573 - 29580
  • [25] Realistic Blur Synthesis for Learning Image Deblurring
    Rim, Jaesung
    Kim, Geonung
    Kim, Jungeon
    Lee, Junyong
    Lee, Seungyong
    Cho, Sunghyun
    COMPUTER VISION, ECCV 2022, PT VII, 2022, 13667 : 487 - 503
  • [26] Towards realistic image via function learning
    Masoumeh Zareapoor
    Junhao Zhang
    Jie Yang
    Multimedia Tools and Applications, 2019, 78 : 29573 - 29580
  • [27] MRI super-resolution via realistic downsampling with adversarial learning
    Huang, Bangyan
    Xiao, Haonan
    Liu, Weiwei
    Zhang, Yibao
    Wu, Hao
    Wang, Weihu
    Yang, Yunhuan
    Yang, Yidong
    Miller, G. Wilson
    Li, Tian
    Cai, Jing
    PHYSICS IN MEDICINE AND BIOLOGY, 2021, 66 (20):
  • [28] Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection
    Vitorino, Joao
    Oliveira, Nuno
    Praca, Isabel
    FUTURE INTERNET, 2022, 14 (04)
  • [29] Plausible Counterfactuals: Auditing Deep Learning Classifiers with Realistic Adversarial Examples
    Barredo-Arrieta, Alejandro
    Del Ser, Javier
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [30] Theoretical Analysis of Image-to-Image Translation with Adversarial Learning
    Pan, Xudong
    Zhang, Mi
    Ding, Daizong
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80