DMSH-Net: Depth-aware multi-scale hybrid vision network for image dehazing.

As a fundamental problem in image restoration, single-image dehazing aims to recover clear scene information from fog-degraded observations, improving visual quality and realism []. With the increasing demand for all-weather vision in applications such as autonomous driving [,], drone inspection [,], smart agriculture [,], and remote sensing [,], robust dehazing has become particularly important. However, under hazy conditions, atmospheric scattering causes nonlinear attenuation of scene radiance, leading to low contrast, missing details, and colour distortion [–]. These degradations reduce the reliability of downstream tasks such as semantic segmentation and object detection [–]. Therefore, it is essential to remove haze while preserving textures, edges, and structural details. Traditional dehazing methods mainly rely on the atmospheric scattering model [,,,], which is commonly written as: where () is the observed hazy image, () is the haze-free image, is the transmission map, () is the scene depth, and denotes the global atmospheric light. The exponential form of () reflects the strong nonlineariy of haze, especially in regions with large depth or density variations. Based on the atmospheric scattering model in (1), the dark channel prior (DSP) method was proposed and developed [,,], which estimated the transmission map () based on the assumption tha haze-free images contain low-intensity values in at least one color channel. These prior-based approaches have achieved relatively promising results to a certain extent. However, their reliance on hand-crafted assumptions often results in inaccurate transmission estimation, leading to inadequate performance under complex conditions.