Progressive Depth Learning for Single Image Dehazing

Abstract

The formulation of the hazy image is mainly dominated by the reflected lights and ambient airlight. Existing dehazing methods often ignore the depth cues and fail in distant areas where heavier haze disturbs the visibility. However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase. In turn, the good transmission estimation could facilitate the depth estimation for hazy images. In this paper, a deep end-to-end model that iteratively estimates image depths and transmission maps is proposed to perform an effective depth prediction for hazy images and improve the dehazing performance with the guidance of depth information. The image depth and transmission map are progressively refined to better restore the dehazed image. Our approach benefits from explicitly modeling the inner relationship of image depth and transmission map, which is especially effective for distant hazy areas. Extensive results on the benchmarks demonstrate that our proposed network performs favorably against the state-of-the-art dehazing methods in terms of depth estimation and haze removal.

Self-supervised monocular depth estimation in fog

“…Although the depth estimation performance is improved, the application of feature fusion may not fully benefit from the intrinsic relationship between depth and transmission. In contrast, Liang et al 31 show modeling the relationship between depth and transmission maps, performing progressive depth learning, and iteratively refining the estimates. However, the above method uses the transmission map and depth in an exponential relationship depth estimation in foggy weather, estimates the transmission map as an intermediate step, and then derives the depth map.…”