Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model

TL;DR

A new image restoration model called DescanDiffusion is proposed consisting of a color encoder that corrects the global color degradation and a conditional denoising diffusion probabilistic model that removes local degradations to improve the generalization ability of DescanDiffusion.

Abstract

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.

Figures (3)

• Figure 1: Examples of degradations in DESCAN-18K. Both (a) and (e) are scanned examples in DESCAN-18K. From (b) to (h), except for (e), patches in the upper row with orange dotted lines are from original images, and patches in the lower row with blue dotted lines are from their scanned counterpart (See the supplementary material for more diverse examples).
• Figure 2: Overview of our DescanDiffusion: (a) the whole process of DescanDiffusion with global color correction and local generative refinement modules; (b) global color correction module with a color encoder that predicts the color correction vector $v_c$ and produces the color-corrected image $I_c$; (c) the training process of the local generative refinement module with a conditional DDPM.
• Figure 3: Qualitative comparisons of descanning performance on DESCAN-18K testing set. Scanned images (denoted as Scanned) in each row mostly have the following degradations; $1^{st}$ row: texture distortion, color transition, and internal noises in a linear laser form, $2^{nd}$ row: color transition and texture distortion, $3^{rd}$ row: same degradations in the $1^{st}$ row. Our DescanDiffusion+ model outperforms another image-to-image translation model, real-world photo restoration model, recent image restoration model, and commercial product in handling degradations in text regions, natural scenes, and screen contents (See the supplementary material for more diverse examples).