CycleGAN has been proven to be an advanced approach for unsupervised image restoration. This framework consists of two generators: a denoising one for inference and an auxiliary one for modeling noise to fulfill cycle-consistency constraints. However, when applied to the infrared destriping task, it becomes challenging for the vanilla auxiliary generator to consistently produce vertical noise under unsupervised constraints. This poses a threat to the effectiveness of the cycle-consistency loss, leading to stripe noise residual in the denoised image. To address the above issue, we present a novel framework for single-frame infrared image destriping, named DestripeCycleGAN. In this model, the conventional auxiliary generator is replaced with a priori stripe generation model (SGM) to introduce vertical stripe noise in the clean data, and the gradient map is employed to re-establish cycle-consistency. Meanwhile, a Haar wavelet background guidance module (HBGM) has been designed to minimize the divergence of background details between the different domains. To preserve vertical edges, a multi-level wavelet U-Net (MWUNet) is proposed as the denoising generator, which utilizes the Haar wavelet transform as the sampler to decline directional information loss. Moreover, it incorporates the group fusion block (GFB) into skip connections to fuse the multi-scale features and build the context of long-distance dependencies. Extensive experiments on real and synthetic data demonstrate that our DestripeCycleGAN surpasses the state-of-the-art methods in terms of visual quality and quantitative evaluation. Our code will be made public at https://github.com/0wuji/DestripeCycleGAN.

翻译：循环生成对抗网络已被证明是一种先进的无监督图像复原方法。该架构包含两个生成器：一个用于推理的去噪生成器，以及一个用于模拟噪声以满足循环一致性约束的辅助生成器。然而，当应用于红外去条纹任务时，原始辅助生成器在无监督约束下难以持续生成垂直噪声，这会威胁循环一致性损失的有效性，导致去噪图像中残留条纹噪声。为解决上述问题，我们提出了一种名为DestripeCycleGAN的新型单帧红外图像去条纹框架。在该模型中，传统辅助生成器被替换为先验条纹生成模型，用于在干净数据中引入垂直条纹噪声，并利用梯度图重建循环一致性。同时，设计了哈尔小波背景引导模块，以最小化不同域之间背景细节的差异。为保留垂直边缘，提出多级小波U-Net作为去噪生成器，该网络利用哈尔小波变换作为采样器以减少方向信息损失。此外，在跳跃连接中引入组融合块，以融合多尺度特征并建立长距离依赖上下文。在真实与合成数据上的大量实验表明，我们的DestripeCycleGAN在视觉质量和定量评估方面均超越了现有最先进方法。我们的代码将开源在https://github.com/0wuji/DestripeCycleGAN。