Improved Single Image Dehazing Using Guided Filter

Single image dehazing is challenging because it is massively ill-posed. Haze removal based on dark channel prior is effective, but refining the transmission map with closed-form matting is computationally expensive. Recent work discovered that using guided filter to refine the transmission map is feasible. In this paper, we elaborate single image dehazing by combining dark channel prior and guided image filtering in detail. By analyzing the tradeoffs of this approach, we propose an effective scheme to adapt the parameters. Experiments and comparisons show that our method generates satisfactory dehazed results with low computation.