High-resolution Document Shadow Removal via A Large-scale Real-world Dataset and A Frequency-aware Shadow Erasing Net

Shadows often occur when we capture the document with casual equipment, which influences the visual quality and readability of the digital copies. Different from the algorithms for natural shadow removal, the algorithms in document shadow removal need to preserve the details of fonts and figures in high-resolution input. Previous work ignores this problem and removes the shadow via a low-resolution approximate attention and small datasets, which might not work in real-world situations. We handle high-resolution document shadow removal directly via a carefully-designed frequency-aware network and a larger-scale real-world dataset. As for the dataset, we acquire over 7k couples of high-resolution (2462 x 3699) images of real-world documents with various samples under different lighting circumstances, which is 10 times larger than existing datasets. As for the design of the network, we decouple the high-resolution images in the frequency domain, where we can learn the low-frequency details and high-frequency boundary individually via the carefully designed network structure. Powered by our network and dataset, the proposed method shows a clearly better performance than previous methods in terms of visual quality and numerical results. The dataset and code is available at here.

This work is supported in part by the University of Macau under Grant MYRG2022-00190-FST, in part by the Science and Technology Development Fund, Macau SAR, under Grant 0034/2019/AMJ, Grant 0087/2020/A2 and Grant 0049/2021/A.