DestripeCycleGAN：用于无监督红外图像去条纹的条纹模拟CycleGAN
DestripeCycleGAN: Stripe Simulation CycleGAN for Unsupervised Infrared Image Destriping
AI总结：
提出DestripeCycleGAN框架，通过先验条纹生成模型和梯度图重建循环一致性，结合Haar小波背景引导模块与多级小波U-Net去噪生成器，有效解决无监督红外图像去条纹任务中的噪声残留问题，在视觉与定量评估上超越现有方法。
摘要：
CycleGAN已被证明是无监督图像恢复的先进方法。该框架包含两个生成器：一个用于推理的去噪生成器和一个用于建模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，原始的辅助生成器在无监督约束下难以持续产生垂直噪声。这威胁到了循环一致性损失的有效性，导致去噪图像中残留条纹噪声。为了解决上述问题，我们提出了一种用于单帧红外图像去条纹的新颖框架，名为DestripeCycleGAN。在该模型中，传统的辅助生成器被先验条纹生成模型（SGM）取代，以在干净数据中引入垂直条纹噪声，并采用梯度图来重新建立循环一致性。同时，设计了Haar小波背景引导模块（HBGM），以最小化不同域之间背景细节的差异。为了保留垂直边缘，提出了一种多级小波U-Net（MWUNet）作为去噪生成器，它利用Haar小波变换作为采样器来减少方向信息丢失。此外，它将组融合块（GFB）融入跳跃连接中，以融合多尺度特征并构建长距离依赖的上下文。在真实和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的方法。我们的代码将在https://github.com/0wuji/DestripeCycleGAN公开。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
