Underwater image enhancement with Image Colorfulness Measure
This work addresses visual quality issues in underwater images for applications like marine research or photography, but it appears incremental as it builds on existing enhancement techniques.
The authors tackled the problem of underwater image degradation by proposing a trainable end-to-end neural model for enhancement, achieving high-quality results in experiments on natural underwater scenes.
Due to the absorption and scattering effects of the water, underwater images tend to suffer from many severe problems, such as low contrast, grayed out colors and blurring content. To improve the visual quality of underwater images, we proposed a novel enhancement model, which is a trainable end-to-end neural model. Two parts constitute the overall model. The first one is a non-parameter layer for the preliminary color correction, then the second part is consisted of parametric layers for a self-adaptive refinement, namely the channel-wise linear shift. For better details, contrast and colorfulness, this enhancement network is jointly optimized by the pixel-level and characteristiclevel training criteria. Through extensive experiments on natural underwater scenes, we show that the proposed method can get high quality enhancement results.