The inaccurate estimation of underwater background light and distortion of scene color results in the lower quality of recovered underwater images. To address this problem, the paper proposes an enhancement algorithm for underwater images based on dark channel theory, which is expected to improve the clarity, contrast and color fidelity of underwater images. Different from the works of others, the paper uses underwater 3-D transmittance map to achieve the effect of deblurring and contrast enhancement of underwater images. The experimental results show that our algorithm can significantly improve the quality of underwater images.