UniRestorer：通过自适应估计适当粒度的图像退化实现通用图像恢复
UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity
AI总结：
提出UniRestorer，通过层次聚类退化空间并训练多粒度MoE模型，结合退化与粒度估计自适应选择专家，大幅提升一体化图像恢复性能，缩小与单任务模型的差距。
摘要：
近年来，一体化图像恢复取得了相当大的进展。通常，现有方法可以是退化无关的或退化感知的。然而，前者在利用退化特定恢复方面受限，后者则遭受退化估计中不可避免的错误。因此，现有方法的性能与特定单任务模型相比存在较大差距。在这项工作中，我们在此主题上向前迈出了一步，提出了具有改进恢复性能的UniRestorer。具体而言，我们对退化空间进行层次聚类，并训练一个多粒度混合专家（MoE）恢复模型。然后，UniRestorer采用退化和粒度估计，自适应地为图像恢复选择合适的专家。与现有的退化无关和退化感知方法相比，UniRestorer可以利用退化估计来促进退化特定恢复，并使用粒度估计使模型对退化估计错误具有鲁棒性。实验结果表明，我们的UniRestorer大幅优于最先进的一体化方法，并有望缩小与特定单任务模型的性能差距。
英文摘要：
Recently, considerable progress has been made in all-in-one image restoration. Generally, existing methods can be degradation-agnostic or degradation-aware. However, the former are limited in leveraging degradation-specific restoration, and the latter suffer from the inevitable error in degradation estimation. Consequently, the performance of existing methods has a large gap compared to specific single-task models. In this work, we make a step forward in this topic, and present our UniRestorer with improved restoration performance. Specifically, we perform hierarchical clustering on degradation space, and train a multi-granularity mixture-of-experts (MoE) restoration model. Then, UniRestorer adopts both degradation and granularity estimation to adaptively select an appropriate expert for image restoration. In contrast to existing degradation-agnostic and -aware methods, UniRestorer can leverage degradation estimation to benefit degradation specific restoration, and use granularity estimation to make the model robust to degradation estimation error. Experimental results show that our UniRestorer outperforms state-of-the-art all-in-one methods by a large margin, and is promising in closing the performance gap to specific single task models.
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。
