results: 实验结果表明，提议的算法在比较难以处理的暴雨情况下可以更好地提高图像特征提取能力，并且比现有方法更高效。Abstract
Rain streaks bring complicated pixel intensity changes and additional gradients, greatly obstructing the extraction of image features from background. This causes serious performance degradation in feature-based applications. Thus, it is critical to remove rain streaks from a single rainy image to recover image features. Recently, many excellent image deraining methods have made remarkable progress. However, these human visual system-driven approaches mainly focus on improving image quality with pixel recovery as loss function, and neglect how to enhance image feature recovery ability. To address this issue, we propose a task-driven image deraining algorithm to strengthen image feature supply for subsequent feature-based applications. Due to the extensive use and strong practicability of Scale-Invariant Feature Transform (SIFT), we first propose two separate networks using distinct losses and modules to achieve two goals, respectively. One is difference of Gaussian (DoG) pyramid recovery network (DPRNet) for SIFT detection, and the other gradients of Gaussian images recovery network (GGIRNet) for SIFT description. Second, in the DPRNet we propose an alternative interest point loss that directly penalizes scale response extrema to recover the DoG pyramid. Third, we advance a gradient attention module in the GGIRNet to recover those gradients of Gaussian images. Finally, with the recovered DoG pyramid and gradients, we can regain SIFT key points. This divide-and-conquer scheme to set different objectives for SIFT detection and description leads to good robustness. Compared with state-of-the-art methods, experimental results demonstrate that our proposed algorithm achieves better performance in both the number of recovered SIFT key points and their accuracy.
摘要
雨束线会导致图像像素强度变化和附加的梯度，大大阻碍图像特征的提取，从背景中。这会导致图像特征提取的性能下降，影响后续的特征基于应用。因此，需要从雨束图像中除除雨束，以恢复图像特征。现在，许多出色的图像抽取方法已经做出了很好的进步。然而，这些人视系统驱动的方法主要关注图像质量的改进，忽略了如何提高图像特征提取能力。为解决这个问题，我们提出了一种任务驱动的图像抽取算法，以增强图像特征供应。由于Scale-Invariant Feature Transform（SIFT）的广泛使用和强大实用性，我们首先提出了两个分开的网络，使用不同的损失函数和模块，分别完成两个目标。一个是Diffusion of Gaussian（DoG） pyramid recovery network（DPRNet），用于SIFT检测；另一个是Gradients of Gaussian images recovery network（GGIRNet），用于SIFT描述。二、在DPRNet中，我们提出了一种alternative interest point损失函数，直接惩罚scale response极值，以恢复DoG pyramid。三、在GGIRNet中，我们提出了一种gradient attention模块，用于恢复Gaussian图像的梯度。最后，通过恢复DoG pyramid和梯度，我们可以重新获得SIFT关键点。这种分解并且分配不同的目标 для SIFT检测和描述，导致良好的Robustness。与现状的方法相比，我们的提出的算法在recovered SIFT关键点的数量和准确性方面具有更好的性能。