一种用于GT-RAIN挑战赛CVPR 2023研讨会UG$^{\textbf{2}}$+赛道3的两阶段真实图像去雨方法
A Two-Stage Real Image Deraining Method for GT-RAIN Challenge CVPR 2023 Workshop UG$^{\textbf{2}}$+ Track 3
AI总结：
提出两阶段真实图像去雨框架，结合低秩视频去雨生成伪真值并微调Uformer网络，在GT-RAIN挑战赛中获SSIM第一、PSNR第二。
摘要：
在本技术报告中，我们简要介绍了我们团队HUST\li VIE在CVPR 2023 UG$^{2}$+赛道3的GT-Rain挑战赛中的解决方案。在此任务中，我们提出了一种高效的两阶段框架，用于从雨天帧中重建清晰图像。首先，利用一种基于低秩的视频去雨方法生成伪真值（pseudo GT），该方法充分利用了多帧且对齐的雨天帧的优势。其次，实现了一种基于Transformer的单图像去雨网络Uformer，先在大型真实雨数据集上进行预训练，然后在伪真值上进行微调，以进一步改善图像恢复效果。此外，为了获得视觉上令人愉悦的效果，在流程末端使用了一个全面的图像处理器模块。我们的整体框架经过精心设计，能够处理最终测试阶段提供的重雨和雾序列。最终，我们在平均结构相似性（SSIM）上排名第一，在平均峰值信噪比（PSNR）上排名第二。我们的代码可在https://github.com/yunguo224/UG2_Deraining获取。
英文摘要：
In this technical report, we briefly introduce the solution of our team HUST\li VIE for GT-Rain Challenge in CVPR 2023 UG$^{2}$+ Track 3. In this task, we propose an efficient two-stage framework to reconstruct a clear image from rainy frames. Firstly, a low-rank based video deraining method is utilized to generate pseudo GT, which fully takes the advantage of multi and aligned rainy frames. Secondly, a transformer-based single image deraining network Uformer is implemented to pre-train on large real rain dataset and then fine-tuned on pseudo GT to further improve image restoration. Moreover, in terms of visual pleasing effect, a comprehensive image processor module is utilized at the end of pipeline. Our overall framework is elaborately designed and able to handle both heavy rainy and foggy sequences provided in the final testing phase. Finally, we rank 1st on the average structural similarity (SSIM) and rank 2nd on the average peak signal-to-noise ratio (PSNR). Our code is available at https://github.com/yunguo224/UG2_Deraining.
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。
