Enhanced Attentive Generative Adversarial Network for Single-Image Deraining
Autor: | Guoqiang Chai, Zhaoba Wang, Guodong Guo, Youxing Chen, Yong Jin, Dawei Wang, Bin Lu, Shilei Ren |
---|---|
Rok vydání: | 2021 |
Předmět: |
General Computer Science
Computer science Feature extraction Normalization (image processing) Stability (learning theory) 02 engineering and technology 010501 environmental sciences 01 natural sciences Image deraining Convolution Image (mathematics) 0202 electrical engineering electronic engineering information engineering General Materials Science relativistic GAN Electrical and Electronic Engineering Representation (mathematics) 0105 earth and related environmental sciences business.industry attentive module Deep learning General Engineering Pattern recognition Autoencoder TK1-9971 020201 artificial intelligence & image processing Electrical engineering. Electronics. Nuclear engineering Artificial intelligence business |
Zdroj: | IEEE Access, Vol 9, Pp 58390-58402 (2021) |
ISSN: | 2169-3536 |
Popis: | The problem of image rain removal has drawn widespread attention as the blurry images caused by rain streaks can degrade the performance of many computer vision tasks. Although exiting deep learning-based methods outperform most traditional methods, there are still unresolved issues in terms of performance. In this paper, we propose a novel enhanced attentive generative adversarial network named EAGAN to effectively remove the rain streaks and restore the image structural details at the same time. As rain streaks have different sizes and shapes, EAGAN utilizes a multiscale aggregation attention module (MAAM) to produce an attention map to guide the subsequent network to put conscious attention to rain regions. A symmetrical autoencoder with long-range skip-connections, squeeze-and-excitation (SE) modules, and non-local operation is further utilized to enhance the representation of the network. Finally, spectral normalization and a relativistic generative adversarial network (GAN) are further applied to improve the training stability and deraining performance. Both qualitative and quantitative validations on synthetic and real-world datasets demonstrate that the proposed approach can achieve a competitive performance in comparison with the state-of-the-art methods. |
Databáze: | OpenAIRE |
Externí odkaz: |