Recovering scenes by polarization analysis

We devise a computer vision approach which removes degradation effects in optical underwater imaging. It exploits natural illumination. By analysis of the physical effects of visibility degradation, we associate natural backscatter with partial polarization of light. This is contrary to prior studies which have associated polarization with light emanating from the objects, rather than the backscatter. Our algorithm takes advantage of this aspect to invert the image formation process. In this paper we show that our method achieves a much better visibility recovery, compared to prior methods. This is demonstrated in underwater experimentation in the sea. In addition, the physics-based analysis of the polarization filtered images recovers a range-map of the scene. This allows 3D rendering of the scene from various viewpoints