<p>Due to the light scattering and absorption caused by water molecules and suspended particles, underwater imaging will be seriously affected in terms of color fidelity and contrast, which significantly degrades image quality. In order to solve these problems, we propose an underwater image restoration method based on a constrained color compensation and the haze-line model. First, the color-corrected underwater image is converted to a color space with background light intensity set as the origin. In this space, the pixels with similar color features are grouped by superpixel clustering to identify all haze-lines. Then, the transmission distribution is estimated based on the identified haze-lines, and the estimated value is substituted into the underwater scattering model and applied to the brightness channel of the underwater image after color correction to remove the scattered light component. Finally, the visual quality of the image is improved by adaptive gamma correction. Experiments on datasets such as UCCS shows that our algorithm has better color fidelity and contrast, and improves both subjective visual quality and objective indicators (e.g., UCIQE, UIQM).</p>