双路径多尺度Transformer用于高质量图像去雨
Dual-Path Multi-Scale Transformer for High-Quality Image Deraining
AI总结：
本文提出双路径多尺度Transformer（DPMformer），结合粗到细下采样与多块堆叠策略，利用多尺度信息实现高质量图像去雨，并在基准数据集上超越现有方法。
摘要：
尽管卷积神经网络（CNNs）和Transformer在单图像去雨方面表现出优越性，但当前的多尺度模型由于依赖单尺度特征金字塔模式，仍面临重大挑战。在本文中，我们提出了一种有效的去雨方法，即双路径多尺度Transformer（DPMformer），通过利用丰富的多尺度信息实现高质量图像重建。该方法由一个主干路径和两个来自不同多尺度方法的分支路径组成。具体而言，一条路径采用从粗到细的策略，逐步将图像下采样至1/2和1/4尺度，这有助于捕获细尺度的潜在雨信息融合。同时，我们在另一条路径中采用多块堆叠模型（大小为2和4的非重叠块）来丰富深度网络的特征信息。为了学习更丰富的特征混合，主干路径充分利用多尺度信息以实现高质量的去雨图像重建。在基准数据集上的大量实验表明，与其他最先进的方法相比，我们的方法取得了有前景的性能。
英文摘要：
Despite the superiority of convolutional neural networks (CNNs) and Transformers in single-image rain removal, current multi-scale models still face significant challenges due to their reliance on single-scale feature pyramid patterns. In this paper, we propose an effective rain removal method, the dual-path multi-scale Transformer (DPMformer) for high-quality image reconstruction by leveraging rich multi-scale information. This method consists of a backbone path and two branch paths from two different multi-scale approaches. Specifically, one path adopts the coarse-to-fine strategy, progressively downsampling the image to 1/2 and 1/4 scales, which helps capture fine-scale potential rain information fusion. Simultaneously, we employ the multi-patch stacked model (non-overlapping blocks of size 2 and 4) to enrich the feature information of the deep network in the other path. To learn a richer blend of features, the backbone path fully utilizes the multi-scale information to achieve high-quality rain removal image reconstruction. Extensive experiments on benchmark datasets demonstrate that our method achieves promising performance compared to other state-of-the-art methods.
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。
