Single Image De-Raining via Improved Generative Adversarial Nets

被引:11
|
作者
Ren, Yi [1 ]
Nie, Mengzhen [2 ]
Li, Shichao [2 ]
Li, Chuankun [3 ]
机构
[1] CAEIT, Beijing 100041, Peoples R China
[2] Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300011, Peoples R China
[3] North Univ China, Sch Informat & Commun Engn, Taiyuan 030051, Peoples R China
关键词
image de-raining; generative adversarial network; rain estimation; refinement network; QUALITY ASSESSMENT; NETWORKS;
D O I
10.3390/s20061591
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Capturing images under rainy days degrades image visual quality and affects analysis tasks, such as object detection and classification. Therefore, image de-raining has attracted a lot of attention in recent years. In this paper, an improved generative adversarial network for single image de-raining is proposed. According to the principles of divide-and-conquer, we divide an image de-raining task into rain locating, rain removing, and detail refining sub-tasks. A multi-stream DenseNet, termed as Rain Estimation Network, is proposed to estimate the rain location map. A Generative Adversarial Network is proposed to remove the rain streaks. A Refinement Network is proposed to refine the details. These three models accomplish rain locating, rain removing, and detail refining sub-tasks, respectively. Experiments on two synthetic datasets and real world images demonstrate that the proposed method outperforms state-of-the-art de-raining studies in both objective and subjective measurements.
引用
收藏
页数:15
相关论文
共 50 条
  • [41] ERL-Net: Entangled Representation Learning for Single Image De-Raining
    Wang, Guoqing
    Sun, Changming
    Sowmya, Arcot
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 5643 - 5651
  • [42] Successive Graph Convolutional Network for Image De-raining
    Fu, Xueyang
    Qi, Qi
    Zha, Zheng-Jun
    Ding, Xinghao
    Wu, Feng
    Paisley, John
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2021, 129 (05) : 1691 - 1711
  • [43] Improving De-raining Generalization via Neural Reorganization
    Xiao, Jie
    Zhou, Man
    Fu, Xueyang
    Liu, Aiping
    Zha, Zheng-Jun
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 4967 - 4976
  • [44] Emotional facial expression transfer from a single image via generative adversarial nets
    Qiao, Fengchun
    Yao, Naiming
    Jiao, Zirui
    Li, Zhihao
    Chen, Hui
    Wang, Hongan
    COMPUTER ANIMATION AND VIRTUAL WORLDS, 2018, 29 (3-4)
  • [45] Single-image de-raining with a connected multi-stream neural network
    Pan Y.
    Shin H.
    Shin, Hyunchul (shin@hanyang.ac.kr), 2020, Institute of Electronics Engineers of Korea (09): : 461 - 467
  • [46] Single-image de-raining using low-rank matrix approximation
    Luo, Yu
    Ling, Jie
    NEURAL COMPUTING & APPLICATIONS, 2020, 32 (11): : 7503 - 7514
  • [47] Single-image de-raining using low-rank matrix approximation
    Yu Luo
    Jie Ling
    Neural Computing and Applications, 2020, 32 : 7503 - 7514
  • [48] Rain-component-aware capsule-GAN for single image de-raining
    Yang, Fei
    Ren, Jianfeng
    Lu, Zheng
    Zhang, Jialu
    Zhang, Qian
    PATTERN RECOGNITION, 2022, 123
  • [49] Multi-scale encoding-decoding model for single image de-raining
    Zhang X.
    Li J.
    Chu Y.
    Tang Y.
    Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition), 2021, 49 (07): : 68 - 73
  • [50] Image de-raining based on octave convolution and attention mechanism
    Yang Q.
    Yu M.
    Fu Q.
    Yan G.
    Kongzhi yu Juece/Control and Decision, 2023, 38 (12): : 3372 - 3380