CA-GAN: Class-Condition Attention GAN for Underwater Image Enhancement

Abstract

Underwater images suffer from serious color distortion and detail loss because of the wavelength-dependent light absorption and scattering, which seriously influences the subsequent underwater object detection and recognition. The latest methods for underwater image enhancement are based on deep models, which focus on finding a mapping function from the underwater image subspace to a ground-truth image subspace. They neglect the diversity of underwater conditions which leads to different background colors of underwater images. In this paper, we propose a Class-condition Attention Generative Adversarial Network (CA-GAN) to enhance an underwater image. We build an underwater image dataset which contains ten categories generated by the simulator with different water attenuation coefficient and depth. Relying on the underwater image classes, CA-GAN creates a many-to-one mapping function for an underwater image. Moreover, in order to generate the realistic image, attention mechanism is utilized. In the channel attention block, the feature maps in the front-end layers and the back-end layers are fused along channels, and in the spatial attention block, feature maps are pixel-wise fused. Extensive experiments are conducted on synthetic and real underwater images. The experimental results demonstrate that CA-GAN can effectively recover color and detail of various scenes of underwater images and is superior to the state-of-the-art methods.

Color Correction and Local Contrast Enhancement for Underwater Image Enhancement

“…Deep learning was gradually emerging and applied in various fields, and underwater image enhancement [41]- [43] is no exception. Perez et al [41] used a convolutional neural network (CNN) for image enhancement for the first time.…”

“…Zong et al [42] proposed an enhancement algorithm based on CycleGAN to enhance the robustness and adaptability of the network. Wang et al [43] suggested using the CA-GAN method for image enhancement. First, underwater degraded images with different attenuation coefficients and depths are synthesized according to the physical model, and then CA-GAN is used to create a manyto-one mapping function, and an attention mechanism is also introduced to improve the visual effect of the image.…”

Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement

“…Guo et al [44] improved the quality of underwater images by a multi-scale dense generative adversarial network. Other relevant works of data-driven UIE methods can be found in [45], [46], [47].…”

Attribute-Aware Generative Design With Generative Adversarial Networks

“…Since its introduction in 2014, GAN [17] continues to attract growing interests in the deep learning community and has been applied to various domains such as computer vision [28]- [33], natural language processing [34], [35], time series synthesis [36], [37], and semantic segmentation [38], [39]. Specifically, GAN has shown significant recent success in the field of computer vision on a variety of tasks such as image generation [28], [29], image to image translation [30], [31], and image super-resolution [32], [33]. The standard GAN structure comprises two neural networks: a generator G and a discriminator D which are iteratively trained by competing against each other in a minimax game, where the generator attempts to produce realistic samples while the discriminator attempts to distinguish the fake samples from the real ones.…”