联合去噪与插值，提升单帧偏振图像质量
CPDDNet: Color-Polarization Denoising and Demosaicking Network
- 设计联合网络，同步处理偏振图像去噪与插值
- 在真实数据集上显著提升图像质量和偏振参数精度
- 适合低光条件下偏振成像应用的科研与工程人员
使用颜色-偏振滤波阵列（CPFA）传感器的彩色偏振成像可在单次曝光中捕捉场景的纹理（颜色强度）与物理（偏振）信息，广泛应用于计算机视觉。然而，CPFA传感器输出的原始马赛克图像常因严重噪声和分辨率损失而退化，尤其在低光照条件下。现有方法通常仅关注去噪或插值任务，未能捕捉二者间的耦合关系，也忽略了共享的底层特征。本文提出一种颜色-偏振去噪与插值网络（CPDDNet），采用特征融合模块，在去噪和插值两个阶段均保留来自CPFA原始数据的特征，实现联合优化。实验结果表明，该方法在真实数据集上显著提升了图像质量与偏振参数准确性，优于现有方法。
原文摘要 · Abstract (English)
Color-polarization imaging using a color-polarization filter array (CPFA) sensor captures both texture (color intensity) and physical (polarization) information of the scene in a single shot, enabling various applications in computer vision. However, the raw mosaic output from a CPFA sensor often suffers from severe noise and resolution loss, especially under low-light conditions. Existing methods generally focus on either denoising or demosaicking tasks, failing to capture the coupling between them and neglecting shared low-level features. In this paper, we propose a color-polarization denoising and demosaicking network (CPDDNet), which is a joint framework that performs noise removal and CPFA interpolation using a feature fusion module that retains the features from the CPFA raw data at both the denoising and the demosaicking stages. Experimental results demonstrate that CPDDNet significantly enhances image quality and polarization parameter accuracy, outperforming existing approaches on a real dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。