Saved in:
Bibliographic Details
Main Authors: Cha, Junghun, Haider, Ali, Yang, Seoyun, Jin, Hoeyeong, Yang, Subin, Uddin, A. F. M. Shahab, Kim, Jaehyoung, Kim, Soo Ye, Bae, Sung-Ho
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.05350
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910322387845120
author Cha, Junghun
Haider, Ali
Yang, Seoyun
Jin, Hoeyeong
Yang, Subin
Uddin, A. F. M. Shahab
Kim, Jaehyoung
Kim, Soo Ye
Bae, Sung-Ho
author_facet Cha, Junghun
Haider, Ali
Yang, Seoyun
Jin, Hoeyeong
Yang, Subin
Uddin, A. F. M. Shahab
Kim, Jaehyoung
Kim, Soo Ye
Bae, Sung-Ho
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05350
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model
Cha, Junghun
Haider, Ali
Yang, Seoyun
Jin, Hoeyeong
Yang, Subin
Uddin, A. F. M. Shahab
Kim, Jaehyoung
Kim, Soo Ye
Bae, Sung-Ho
Computer Vision and Pattern Recognition
Image and Video Processing
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.
title Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2402.05350