利用相位信息提升图像去模糊性能，显著改善噪声和数据少时的效果。
Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring
- 通过分解振幅与相位，改进模糊图像的恢复机制。
- 在GoPro、RealBlur等数据集上优于现有最先进方法，尤其在高噪声下表现更优。
- 适合低样本和高噪声场景下的图像恢复任务。
传统图像去模糊方法直接恢复空间域图像，本文提出一种振幅与相位分解方法，强调精确相位估计对恢复清晰细节的重要性。首先设计了新的线性最小均方误差（LMMSE）估计算法，用于估计模糊含噪图像的振幅与相位。随后采用迭代优化算法，结合前述估计器恢复清晰图像。最后，将算法中原本统计确定且固定的矩阵参数，改用干净与退化图像对的训练数据进行学习，实现端到端训练。该去模糊框架命名为UPADNet（Unrolled Phase and Amplitude Decomposition Network），每个迭代步骤均参数化并可训练。在GoPro、RealBlur及COCO等基准数据集上的实验表明，UPADNet优于基于算法展开的当前最先进深度网络。其优势在高噪声和小样本训练条件下尤为突出。
原文摘要 · Abstract (English)
While most image deblurring techniques directly restore the spatial image variable, we propose an amplitude and phase decomposition recognizing the importance of accurate phase estimation in recovering sharp image details. To that end, we first develop novel linear minimum mean squared (LMMSE) estimators of the amplitude and phase of the blurred, noisy image observation. An iterative optimization algorithm follows that recovers the sharp image using the aforementioned LMMSE estimators. Finally, matrix parameters that are statistically determined and fixed in the iterative algorithm are now learned using a training dataset of clean and degraded observations. Our deblurring engine is dubbed UPADNet (Unrolled Phase and Amplitude Decomposition Network), such that each iteration of the underlying phase and amplitude recovery algorithm is parameterized and trained end-to-end. Experiments over benchmark evaluation datasets such as GoPro, RealBlur and COCO datasets confirm that UPADNet outperforms state of the art deep networks including those based on algorithm unrolling in the image domain. The benefits of UPADNet are even more pronounced in high noise and limited training data regimes.
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。