The common dehazing algorithms always assume that the transmission values of all the pixels in an image block are the same (local consistency assumption). However, it is easy to appear “halo” for image regions where the depth changes obviously. In this paper, we calculate the transmission of each pixel separately without the local consistency assumption. First, we initialize a random transmission value for each pixel in the whole image. Then, we optimize the transmission values through several iterations by minimizing an energy function, which contains the data term and penalty term. In each iteration, we take two procedures of propagation and random search to optimize transmission values. Finally, we use the optimized transmission and the estimated atmospheric light to calculate the haze-free image. Comparison experiments show that our algorithm can remove haze effectively, and obtain the best performance.

常见的除雾算法始终假定图像块中所有像素的透射值相同（局部一致性假设）。但是，对于深度变化明显的图像区域，很容易出现“光晕”。在本文中，我们在没有局部一致性假设的情况下分别计算每个像素的透射率。首先，我们为整个图像中的每个像素初始化一个随机透射值。然后，我们通过最小化包含数据项和惩罚项的能量函数，通过几次迭代来优化传输值。在每次迭代中，我们采用传播和随机搜索两个过程来优化传输值。最后，我们使用优化的透射率和估计的大气光来计算无雾图像。