去扫描：利用颜色校正扩散模型从扫描图像恢复原始图像
Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model
AI总结：
本文提出“去扫描”问题，构建DESCAN-18K数据集，并设计DescanDiffusion模型（颜色编码器加条件扩散模型）以有效恢复扫描图像，优于商业产品。
摘要：
大量的模拟信息（即文档和图像）已以扫描副本的形式数字化，以便在数字世界中存储、共享和/或分析。然而，这些内容的质量因物理世界中的打印、存储和扫描过程引起的各种失真而严重下降。尽管从扫描副本中恢复高质量内容已成为许多产品不可或缺的任务，但这一问题尚未得到系统探索，而且据我们所知，没有公开数据集可用。在本文中，我们将此问题定义为“去扫描”（Descanning），并引入了一个名为DESCAN-18K的新型高质量大规模数据集。该数据集包含在野外收集的18K对原始图像和扫描图像，其中包含多种复杂的退化。为了消除这些复杂的退化，我们提出了一种名为DescanDiffusion的新型图像恢复模型，该模型由一个校正全局颜色退化的颜色编码器和一个去除局部退化的条件去噪扩散概率模型（DDPM）组成。为了进一步提高DescanDiffusion的泛化能力，我们还设计了一种合成数据生成方案，通过再现扫描图像中的显著退化来实现。我们通过全面的实验和分析证明，我们的DescanDiffusion在客观和主观上都优于其他基线方法，包括商业恢复产品。
英文摘要：
A significant volume of analog information, i.e., documents and images, have been digitized in the form of scanned copies for storing, sharing, and/or analyzing in the digital world. However, the quality of such contents is severely degraded by various distortions caused by printing, storing, and scanning processes in the physical world. Although restoring high-quality content from scanned copies has become an indispensable task for many products, it has not been systematically explored, and to the best of our knowledge, no public datasets are available. In this paper, we define this problem as Descanning and introduce a new high-quality and large-scale dataset named DESCAN-18K. It contains 18K pairs of original and scanned images collected in the wild containing multiple complex degradations. In order to eliminate such complex degradations, we propose a new image restoration model called DescanDiffusion consisting of a color encoder that corrects the global color degradation and a conditional denoising diffusion probabilistic model (DDPM) that removes local degradations. To further improve the generalization ability of DescanDiffusion, we also design a synthetic data generation scheme by reproducing prominent degradations in scanned images. We demonstrate that our DescanDiffusion outperforms other baselines including commercial restoration products, objectively and subjectively, via comprehensive experiments and analyses.
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。
