Li Ning, Wang Binglu, Goudail Francois, Zhao Yongqiang, Pan Quan
IEEE Trans Image Process. 2023;32:5961-5976. doi: 10.1109/TIP.2023.3327590. Epub 2023 Nov 7.
Denoising and demosaicking long-wave infrared (LWIR) division-of-focal-plane (DoFP) polarization images are crucial for various vision applications. However, existing methods rely on the sequential application of individual denoising and demosaicking processes, which may result in the accumulation of errors produced by each process. To address this issue, we propose a joint denoising and demosaicking method for LWIR DoFP images based on a three-stage progressive deep convolutional neural network. To ensure the generalization ability of this network, it is essential to have adequate training data that closely resembles real data. Therefore, we model the complex noise sources that affect LWIR DoFP images as mixed Poisson-Additive-Stripe noise and construct a least-squares problem based on the polarization measurement redundancy error to estimate the parameters of this model on real images. Subsequently, the estimated noise parameters are used to generate training data that enables the network to learn accurate polarization image statistics and improve its generalization ability. The experimental results demonstrate the effectiveness of the proposed method in enhancing the image restoration performance on real LWIR DoFP polarization data.
对长波红外（LWIR）焦平面分割（DoFP）偏振图像进行去噪和去马赛克处理对于各种视觉应用至关重要。然而，现有方法依赖于单独的去噪和去马赛克过程的顺序应用，这可能会导致每个过程产生的误差累积。为了解决这个问题，我们提出了一种基于三阶段渐进式深度卷积神经网络的LWIR DoFP图像联合去噪和去马赛克方法。为了确保该网络的泛化能力，拥有与真实数据非常相似的足够训练数据至关重要。因此，我们将影响LWIR DoFP图像的复杂噪声源建模为混合泊松 - 加性 - 条纹噪声，并基于偏振测量冗余误差构建一个最小二乘问题，以在真实图像上估计该模型的参数。随后，使用估计的噪声参数生成训练数据，使网络能够学习准确的偏振图像统计信息并提高其泛化能力。实验结果证明了所提方法在增强真实LWIR DoFP偏振数据的图像恢复性能方面的有效性。
