Image restoration under severe weather is a challenging task. Most of the past works focused on removing rain and haze phenomena in images. However, snow is also an extremely common atmospheric phenomenon that will seriously affect the performance of high-level computer vision tasks, such as object detection and semantic segmentation. Recently, some methods have been proposed for snow removing, and most methods deal with snow images directly as the optimization object. However, the distribution of snow location and shape is complex. Therefore, failure to detect snowflakes / snow streak effectively will affect snow removing and limit the model performance. To solve these issues, we propose a Snow Mask Guided Adaptive Residual Network (SMGARN). Specifically, SMGARN consists of three parts, Mask-Net, Guidance-Fusion Network (GF-Net), and Reconstruct-Net. Firstly, we build a Mask-Net with Self-pixel Attention (SA) and Cross-pixel Attention (CA) to capture the features of snowflakes and accurately localized the location of the snow, thus predicting an accurate snow mask. Secondly, the predicted snow mask is sent into the specially designed GF-Net to adaptively guide the model to remove snow. Finally, an efficient Reconstruct-Net is used to remove the veiling effect and correct the image to reconstruct the final snow-free image. Extensive experiments show that our SMGARN numerically outperforms all existing snow removal methods, and the reconstructed images are clearer in visual contrast. All codes will be available.
翻译:在恶劣天气下恢复图像是一项艰巨的任务。 过去的大部分工作都侧重于清除图像中的雨和烟雾现象。 但是,雪也是一个极为常见的大气现象,将严重影响高级计算机视觉任务(如物体探测和语义分割)的性能。最近,提出了一些消除雪的方法,而且大多数方法都直接处理作为优化对象的雪图象。然而,雪位和形状的分布是复杂的。因此,如果未能有效地发现雪花/雪流雪,将影响雪花的去掉,并限制模型的性能。为了解决这些问题,我们提议建立一个雪面滑动适应残余图像网络(SMGARN)。具体地说,SMGARN由三个部分组成,如物体探测和语义分隔网络(GF-Net),以及Reconstruc-Net。首先,我们用自像关注(SA)和十字象关注(CAA)来捕捉雪花的特性,并准确定位雪雪场的位置,从而预测一个准确的雪面遮挡。第二,预测的雪面图纸面遮挡系统由三个部分组成,SGMAR网络(G-F-F-F-Net),最终用来变造雪模型,将去除。 将显示现有图像的图解成。最后的SGMGMGMA,将S-real-real-real-S-S-real-real-real-real-real-reaction。S-real-real-regyal-real-reaction。