论文概要
该方法包含 raindrop→streak 和 streak→raindrop 两条互补级联分支，以 attention 融合输出，用 neural architecture search 搜索去雨模块，并提出真实世界 RainDS 数据集。
研究问题
只处理雨丝或只处理镜头雨滴的方法难以覆盖两者同时出现的真实场景，而包含多种雨退化及对应无雨真值的成对真实数据也很少。
论文贡献
- 提出 complementary cascaded network，并行执行两种去除顺序。
- 通过 attention 模块融合互补分支，并自动搜索 deraining architecture。
- 提出 RainDS，包含 rain-streak-only、raindrop-only 和两者同时出现的图像及无雨 ground truth。
证据与评测范围
现有 benchmark 与 RainDS 上的实验报告优于对比 state of the art；准确指标和训练/测试条件应引用 CVPR 论文。
适用范围与局限
框架和 RainDS 覆盖的是搜索空间与数据集中表示的雨类型；对其他天气退化、传感器或无配对部署域的泛化仍是独立问题。
Related work 定位
这不只是笼统的一次联合恢复网络，其关键是两种退化去除顺序的互补级联、attention fusion、architecture search 和真实数据集。
Related Work 表述
Quan 等通过互补级联网络联合处理雨滴与雨丝，融合两种去除顺序，使用 neural architecture search 设计去雨模块，并提出 RainDS 数据集。
这是一段用于说明论文定位的简洁中性表述。
论文官方英文摘要
Existing rain-removal algorithms often tackle either rain streak removal or raindrop removal, and thus may fail to handle real-world rainy scenes. Besides, the lack of real-world deraining datasets comprising different types of rain and their corresponding rain-free ground-truth also impedes deraining algorithm development. In this paper, we aim to address real-world deraining problems from two aspects. First, we propose a complementary cascaded network architecture, namely CCN, to remove rain streaks and raindrops in a unified framework. Specifically, our CCN removes raindrops and rain streaks in a complementary fashion, i.e., raindrop removal followed by rain streak removal and vice versa, and then fuses the results via an attention based fusion module. Considering significant shape and structure differences between rain streaks and raindrops, it is difficult to manually design a sophisticated network to remove them effectively. Thus, we employ neural architecture search to adaptively find optimal architectures within our specified deraining search space. Second, we present a new real-world rain dataset, namely RainDS, to prosper the development of deraining algorithms in practical scenarios. RainDS consists of rain images in different types and their corresponding rain-free ground-truth, including rain streak only, raindrop only, and both of them. Extensive experimental results on both existing benchmarks and RainDS demonstrate that our method outperforms the state-of-the-art.
摘要仅用于学术识别，版权仍归论文作者或出版方所有，不属于本页 CC BY 许可范围。
依据与出处
| 核对内容 | 论文中的位置 |
|---|---|
| 问题陈述 | Abstract |
| 方法与贡献 | Abstract; complementary cascaded network, attention fusion, and NAS sections |
| 评测结论 | Abstract; existing benchmarks and RainDS experiments |
主要核验来源: IEEE version of record (CVPR 2021 version of record; CVF open-access copy has alternate pagination 9147-9156).
如何引用
科研结论应引用论文本身；只有在复用本站原创解读时才引用本页。
Ruijie Quan, Xin Yu, Yuanzhi Liang, and Yi Yang. “Removing Raindrops and Rain Streaks in One Go.” 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 9143-9152. https://doi.org/10.1109/CVPR46437.2021.00903.
复用许可
本页原创解读采用 CC BY 4.0：复用时须署名并链接本页。论文标题、摘要、图表和书目信息不在此许可范围内，仍保留原有权利。 Creative Commons Attribution 4.0 International.