The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such degradation is further exacerbated when applying the models trained on synthetic data to real-world rainy images. We observe two types of domain gaps between synthetic and real-world rainy images: one exists in rain streak patterns; the other is the pixel-level appearance of rain-free images. To bridge the two domain gaps, we propose a semi-supervised detail-recovery image deraining network (Semi-DRDNet) with dual sample-augmented contrastive learning. Semi-DRDNet consists of three sub-networks:i) for removing rain streaks without remnants, we present a squeeze-and-excitation based rain residual network; ii) for encouraging the lost details to return, we construct a structure detail context aggregation based detail repair network; to our knowledge, this is the first time; and iii) for building efficient contrastive constraints for both rain streaks and clean backgrounds, we exploit a novel dual sample-augmented contrastive regularization network.Semi-DRDNet operates smoothly on both synthetic and real-world rainy data in terms of deraining robustness and detail accuracy. Comparisons on four datasets including our established Real200 show clear improvements of Semi-DRDNet over fifteen state-of-the-art methods. Code and dataset are available at https://github.com/syy-whu/DRD-Net.
翻译:雨中图像内容的复杂程度往往导致最尖端的退缩模型导致图像退化,包括残余雨,错误地复制细节和扭曲的外观。当将经过合成数据培训的模型应用到真实世界的雨中图像时,这种退化进一步恶化。我们观察到合成和真实世界的雨中图像之间存在两种类型的领域差距:一种是雨量模式;另一种是无雨图像的像素级外观。为了缩小这两个领域的差距,我们提议建立一个半监督的详细退缩图像网络(Semi-DRDNet),具有双重样本放大的对比性学习。半DRDNet由三个子网络组成:一) 用于清除雨水痕迹,而没有残余,我们展示一个基于挤压和刺激的雨残留网络;二) 为了鼓励丢失的细节返回,我们根据细节修复网络构建一个结构细节汇总;根据我们的知识,这是第一次;以及三) 为雨水流和清洁背景建立高效的对比度图像脱线网络(Semi-Dreal-deal-deal develrial degrade developal degal degal develrial dal degal degal degal sal degal commal degal smal commadrisal commal smal commal commal smal commal-wemal smal-wemal smal commal comm smal comm smal commal commal commal smal commal commal smal commal commal smal smal smal commal commal comm smtrament smal smal commal commal commstr smal smal smal smal comm comm sm comm comm commal)建立网络,我们利用了我们利用了比比比比比比比比比,我们现有的数据系统数据系统数据系统数据系统数据系统数据系统数据系统数据系统数据系统,我们现有的数据系统,我们现有的数据系统,我们利用一个新的的清晰数据系统显示了比比比比可展示数据系统数据系统数据系统显示了比制数据系统显示了