优化Transformer结构，让高清图像去运动模糊更高效。
Efficient Transformer for High Resolution Image Motion Deblurring
- 简化架构降低18.4%复杂度，改进注意力机制提升效率。
- 在RealBlur-R等三组数据集上保持竞争力，训练更快收敛。
- 新增频率损失与增强变换，提升模型鲁棒性，适合实际应用。
本文针对高分辨率图像运动模糊去模糊问题，对Restormer架构进行了系统研究与改进。通过引入架构优化，使模型复杂度降低18.4%，同时在性能上保持或提升。改进的训练流程加入了色彩抖动、高斯模糊和透视变换等增强策略，并提出新的频率损失项以提升模型鲁棒性。在RealBlur-R、RealBlur-J和超高清运动模糊（UHDM）数据集上的大量实验表明，所提方法具有更好的收敛特性与更短的训练时间，且在复杂场景下表现优异。详细的消融实验分析了各项改进对模型行为的影响。结果表明，合理简化架构并结合强化训练策略，可实现更高效且性能相当的去模糊模型。代码与数据见：https://github.com/hamzafer/image-deblurring。
原文摘要 · Abstract (English)
This paper presents a comprehensive study and improvement of the Restormer architecture for high-resolution image motion deblurring. We introduce architectural modifications that reduce model complexity by 18.4% while maintaining or improving performance through optimized attention mechanisms. Our enhanced training pipeline incorporates additional transformations including color jitter, Gaussian blur, and perspective transforms to improve model robustness as well as a new frequency loss term. Extensive experiments on the RealBlur-R, RealBlur-J, and Ultra-High-Definition Motion blurred (UHDM) datasets demonstrate the effectiveness of our approach. The improved architecture shows better convergence behavior and reduced training time while maintaining competitive performance across challenging scenarios. We also provide detailed ablation studies analyzing the impact of our modifications on model behavior and performance. Our results suggest that thoughtful architectural simplification combined with enhanced training strategies can yield more efficient yet equally capable models for motion deblurring tasks. Code and Data Available at: https://github.com/hamzafer/image-deblurring
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。