GridFormer：面向恶劣天气条件下图像复原的带网格结构的残差密集Transformer
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions
AI总结：
针对恶劣天气下图像复原难题，提出基于网格结构与残差密集Transformer块的GridFormer框架，通过增强注意力机制和RDTB提升特征学习能力，在五类图像复原任务上达到SOTA水平。
摘要：
恶劣天气条件下的图像复原是计算机视觉中的一项难题。本文提出了一种名为GridFormer的新型基于Transformer的框架，作为恶劣天气下图像复原的骨干网络。GridFormer采用网格结构设计，使用残差密集Transformer块，并引入两项核心设计。首先，它在Transformer层中使用了增强型注意力机制：该机制包含采样器阶段和紧凑自注意力阶段以提升效率，以及一个局部增强阶段以强化局部信息。其次，我们引入残差密集Transformer块（RDTB）作为GridFormer的最终层，该设计进一步提升了网络从先前和当前局部特征中学习有效特征的能力。GridFormer框架在五种不同的恶劣天气图像复原任务上取得了当前最优（SOTA）结果，包括图像去雨、去雾、去雨去雾、去雪以及多天气复原。源代码和预训练模型可在https://github.com/TaoWangzj/GridFormer获取。
英文摘要：
Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather conditions. GridFormer is designed in a grid structure using a residual dense transformer block, and it introduces two core designs. First, it uses an enhanced attention mechanism in the transformer layer. The mechanism includes stages of the sampler and compact self-attention to improve efficiency, and a local enhancement stage to strengthen local information. Second, we introduce a residual dense transformer block (RDTB) as the final GridFormer layer. This design further improves the network's ability to learn effective features from both preceding and current local features. The GridFormer framework achieves state-of-the-art results on five diverse image restoration tasks in adverse weather conditions, including image deraining, dehazing, deraining \& dehazing, desnowing, and multi-weather restoration. The source code and pre-trained models are available at https://github.com/TaoWangzj/GridFormer.
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。
