arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00823cs.CVcs.GReess.IV
收藏

重新思考通过雨条纹和蒸汽的图像脱轨

Rethinking Image Deraining via Rain Streaks and Vapors

University of Electronic Science and Technology of China(电子科技大学);Tencent AI Lab(腾讯人工智能实验室);MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University(上海交通大学人工智能研究院教育部人工智能重点实验室)

Yinglong Wang, Yibing Song, Chao Ma, Bing Zeng

摘要:

单个图像去渲染将输入图像视为背景图像、透射图、雨条纹和大气光的融合。虽然提出了用于图像复原的高级模型(即,背景图像生成),他们将具有相同属性的雨条纹视为背景,而不是传输介质。作为蒸气(即,雨条纹积累或雾状雨)在透射图中被传送以模拟面纱效应,雨条纹和蒸汽的融合不能自然地反映雨图像形成。在这项工作中,我们重新制定雨条纹作为传输介质与蒸汽模型雨成像。我们提出了一个编码器-解码器CNN命名为SNet学习雨条纹的传输图。由于雨条纹以各种形状和方向出现,我们使用SNet中的ShuffleNet单元来捕获它们的各向异性表示。由于水汽是由雨带带来的,我们提出了一个包含空间金字塔池(SSP)的VNet来预测水汽在多尺度下的传输图。同时,我们使用一个编码器CNN命名为ANet估计大气光。SNet、VNet和ANet被联合训练以预测用于雨图像复原的透射图和大气光。在基准数据集上的大量实验表明,所提出的视觉模型预测雨纹和水汽的有效性。所提出的去重方法对最先进的去重方法表现良好。

英文摘要:

Single image deraining regards an input image as a fusion of a background image, a transmission map, rain streaks, and atmosphere light. While advanced models are proposed for image restoration (i.e., background image generation), they regard rain streaks with the same properties as background rather than transmission medium. As vapors (i.e., rain streaks accumulation or fog-like rain) are conveyed in the transmission map to model the veiling effect, the fusion of rain streaks and vapors do not naturally reflect the rain image formation. In this work, we reformulate rain streaks as transmission medium together with vapors to model rain imaging. We propose an encoder-decoder CNN named as SNet to learn the transmission map of rain streaks. As rain streaks appear with various shapes and directions, we use ShuffleNet units within SNet to capture their anisotropic representations. As vapors are brought by rain streaks, we propose a VNet containing spatial pyramid pooling (SSP) to predict the transmission map of vapors in multi-scales based on that of rain streaks. Meanwhile, we use an encoder CNN named ANet to estimate atmosphere light. The SNet, VNet, and ANet are jointly trained to predict transmission maps and atmosphere light for rain image restoration. Extensive experiments on the benchmark datasets demonstrate the effectiveness of the proposed visual model to predict rain streaks and vapors. The proposed deraining method performs favorably against state-of-the-art deraining approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑