Nighttime Image Dehazing Based on Variational Decomposition Model
Yun Liu, Zhongsheng Yan, Aimin Wu, Ye Tian, Yuche Li · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2022
Most of existing dehazing algorithms are unable to deal with nighttime hazy scenarios well due to complex degraded factors such as non-uniform illumination, low light and glows. To obtain high-quality image under nighttime haze imaging conditions, we present an effective single nighttime image dehazing framework based on a variational decomposition model to simultaneously address these undesirable issues. First, a variational decomposition model consisting of three regularization terms is proposed to simultaneously decompose a nighttime hazy image into a structure layer, a detail layer and a noise layer. Concretely, we employ ℓ1norm to constrain the structure component, adopt ℓ0sparsity term to enforce the piece-wise continuous of the detail layer, and use ℓ2norm to separate the noise layer. Next, the structure layer is recovered by means of inversing the physical model and the detail layers are revealed in a multi-scale gradient enhancement manner. Finally, the dehazed structure layer and the enhanced detail layers are integrated into a haze-free image. Experimental results show that the proposed framework achieves superior performance on nighttime haze removal and noise suppression compared with several state-of-the-art dehazing techniques.