Enhanced CycleGAN Network with Adaptive Dark Channel Prior for Unpaired Single-Image Dehazing

Abstract

Unpaired single-image dehazing has become a challenging research hotspot due to its wide application in modern transportation, remote sensing, and intelligent surveillance, among other applications. Recently, CycleGAN-based approaches have been popularly adopted in single-image dehazing as the foundations of unpaired unsupervised training. However, there are still deficiencies with these approaches, such as obvious artificial recovery traces and the distortion of image processing results. This paper proposes a novel enhanced CycleGAN network with an adaptive dark channel prior for unpaired single-image dehazing. First, a Wave-Vit semantic segmentation model is utilized to achieve the adaption of the dark channel prior (DCP) to accurately recover the transmittance and atmospheric light. Then, the scattering coefficient derived from both physical calculations and random sampling means is utilized to optimize the rehazing process. Bridged by the atmospheric scattering model, the dehazing/rehazing cycle branches are successfully combined to form an enhanced CycleGAN framework. Finally, experiments are conducted on reference/no-reference datasets. The proposed model achieved an SSIM of 94.9% and a PSNR of 26.95 on the SOTS-outdoor dataset and obtained an SSIM of 84.71% and a PSNR of 22.72 on the O-HAZE dataset. The proposed model significantly outperforms typical existing algorithms in both objective quantitative evaluation and subjective visual effect.

Advancements in Remote Sensing Image Dehazing: Introducing URA-Net with Multi-Scale Dense Feature Fusion Clusters and Gated Jump Connection

“…It is imperative to acknowledge that the diminished intensity observed in the dark channel primarily stems from shadows cast by the scene, the presence of dark objects, and vividly colored surfaces or objects. The dark channel a priori defogging algorithm, grounded in statistical principles, has demonstrated commendable outcomes within the realm of image defogging, exhibiting greater stability in comparison to the aforementioned non-physical model algorithms [34][35][36][37][38]. This algorithm can more accurately estimate the thickness of the fog, resulting in a more natural and clearer defogging effect [39][40][41].…”

Remote Sensing Image Dehazing through an Unsupervised Generative Adversarial Network

“…We use two evaluation indexes, PSNR [40] and SSIM [41], to quantitatively compare our method with other methods. The PSNR can be expressed as:…”

A Method for Identifying Power Equipment in Foggy Substation Based on Improved YOLOv4

“…The Cycle Dehaze [7] image defogging algorithm is an enhanced version of the Cycle GAN [8] . The deep separable convolution in the MobileNetv3 network greatly reduces the parameter size of the backbone network, which is then used to improve the YOLOv4 backbone feature extraction network CSPLocknet53.…”