用于图像去雨的双向多尺度隐式神经表示
Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
AI总结：
本文提出NeRD-Rain，一种结合多尺度Transformer、基于像素坐标的隐式神经表示和尺度间双向反馈的图像去雨方法，在合成与真实数据集上取得领先性能。
摘要：
如何有效探索雨纹的多尺度表示对于图像去雨至关重要。与现有主要依赖单尺度雨纹外观的基于Transformer的方法不同，我们开发了一种端到端的多尺度Transformer，利用各种尺度中潜在有用的特征来促进高质量的图像重建。为了更好地探索空间变化雨纹中的共同退化表示，我们在闭环设计中结合了基于像素坐标的尺度内隐式神经表示与退化输入，使学习到的特征有助于去除雨纹，并提高模型在复杂场景中的鲁棒性。为了确保来自不同尺度的更丰富的协作表示，我们在多尺度Transformer中嵌入了一个简单而有效的尺度间双向反馈操作，通过执行从粗到细和从细到粗的信息通信。大量实验表明，我们的方法名为NeRD-Rain，在合成和真实世界基准数据集上的表现优于最先进的方法。源代码和训练模型可在https://github.com/cschenxiang/NeRD-Rain获取。
英文摘要：
How to effectively explore multi-scale representations of rain streaks is important for image deraining. In contrast to existing Transformer-based methods that depend mostly on single-scale rain appearance, we develop an end-to-end multi-scale Transformer that leverages the potentially useful features in various scales to facilitate high-quality image reconstruction. To better explore the common degradation representations from spatially-varying rain streaks, we incorporate intra-scale implicit neural representations based on pixel coordinates with the degraded inputs in a closed-loop design, enabling the learned features to facilitate rain removal and improve the robustness of the model in complex scenarios. To ensure richer collaborative representation from different scales, we embed a simple yet effective inter-scale bidirectional feedback operation into our multi-scale Transformer by performing coarse-to-fine and fine-to-coarse information communication. Extensive experiments demonstrate that our approach, named as NeRD-Rain, performs favorably against the state-of-the-art ones on both synthetic and real-world benchmark datasets. The source code and trained models are available at https://github.com/cschenxiang/NeRD-Rain.
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。
