Nighttime Image Dehazing Based on Multi-Scale Gated Fusion Network

In this paper, we propose an efficient algorithm to directly restore a clear image from hazy input, which can be adapted for nighttime dehazing. The proposed hinges on trainable neural network realized in encoder–decoder architecture. encoder is exploited capture the context of derived input images, while decoder employed estimate contribution each final dehazed result using learned representations attributed encoder. constructed adopts novel fusion-based strategy derives three inputs original by applying white balance (WB), contrast enhancing (CE), and gamma correction (GC). We compute pixel-wise confidence maps based appearance differences between these different blend information preserve regions with pleasant visibility. generated gating important features inputs. To train network, introduce multi-scale approach avoid halo artifacts. Extensive experimental results both synthetic real-world images demonstrate that performs favorably against state-of-the-art dehazing images.