论文标题
磁带：任务不可能的事先嵌入图像修复
TAPE: Task-Agnostic Prior Embedding for Image Restoration
论文作者
论文摘要
学习自然图像恢复的一般性先验是一项重要但具有挑战性的任务。早期方法主要涉及手工制作的先验，包括归一化稀疏性，L_0梯度，暗通道先验等。最近，深层神经网络已用于学习各种图像先验，但不能保证概括。在本文中，我们提出了一种新颖的方法，该方法将任务不合时宜的先验嵌入到变压器中。我们的方法称为任务不合时宜的先验嵌入（磁带），由两个阶段组成，即任务不合时宜的预训练和特定于任务的微调，其中第一阶段将有关自然图像的先验知识嵌入变压器中，第二阶段将知识提取到知识以帮助下游图像恢复。对各种降解的实验验证了胶带的有效性。在PSNR方面，图像恢复性能提高了多达1.45dB，甚至超过了特定于任务的算法。更重要的是，磁带显示了从退化的图像中解开广义图像先验的能力，这些图像具有良好的转移能力，可以转移到未知的下游任务。
Learning a generalized prior for natural image restoration is an important yet challenging task. Early methods mostly involved handcrafted priors including normalized sparsity, l_0 gradients, dark channel priors, etc. Recently, deep neural networks have been used to learn various image priors but do not guarantee to generalize. In this paper, we propose a novel approach that embeds a task-agnostic prior into a transformer. Our approach, named Task-Agnostic Prior Embedding (TAPE), consists of two stages, namely, task-agnostic pre-training and task-specific fine-tuning, where the first stage embeds prior knowledge about natural images into the transformer and the second stage extracts the knowledge to assist downstream image restoration. Experiments on various types of degradation validate the effectiveness of TAPE. The image restoration performance in terms of PSNR is improved by as much as 1.45dB and even outperforms task-specific algorithms. More importantly, TAPE shows the ability of disentangling generalized image priors from degraded images, which enjoys favorable transfer ability to unknown downstream tasks.
