Deep Underwater Image Enhancement
This work addresses image enhancement for underwater photography, offering a more flexible and automated solution compared to prior methods, though it is incremental as it builds on existing CNN approaches.
The paper tackles the problem of degraded visibility in underwater images due to light absorption and scattering by proposing UWCNN, a convolutional neural network trained on synthetic databases, which outperforms existing methods on real-world and synthetic images with improved generalization across different scenes.
In an underwater scene, wavelength-dependent light absorption and scattering degrade the visibility of images, causing low contrast and distorted color casts. To address this problem, we propose a convolutional neural network based image enhancement model, i.e., UWCNN, which is trained efficiently using a synthetic underwater image database. Unlike the existing works that require the parameters of underwater imaging model estimation or impose inflexible frameworks applicable only for specific scenes, our model directly reconstructs the clear latent underwater image by leveraging on an automatic end-to-end and data-driven training mechanism. Compliant with underwater imaging models and optical properties of underwater scenes, we first synthesize ten different marine image databases. Then, we separately train multiple UWCNN models for each underwater image formation type. Experimental results on real-world and synthetic underwater images demonstrate that the presented method generalizes well on different underwater scenes and outperforms the existing methods both qualitatively and quantitatively. Besides, we conduct an ablation study to demonstrate the effect of each component in our network.