Contextual-assisted scratched photo restoration

Printed photographs can be easily warped, wrinkled, and even deteriorated over time. Existing methods treat the restoration of scratches as a pure inpainting problem that neglects the underlying corrupted contextual knowledge. However, important underlying contents are hidden behind the scratches, w...

Full description

Saved in:
Bibliographic Details
Main Authors: CAI, Weiwei, ZHANG, Huaidong, XU, Xuemiao, HE, Shengfeng, ZHANG, Kun, QIN, Jing
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8377
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9380
record_format dspace
spelling sg-smu-ink.sis_research-93802023-12-12T07:48:03Z Contextual-assisted scratched photo restoration CAI, Weiwei ZHANG, Huaidong XU, Xuemiao HE, Shengfeng ZHANG, Kun QIN, Jing Printed photographs can be easily warped, wrinkled, and even deteriorated over time. Existing methods treat the restoration of scratches as a pure inpainting problem that neglects the underlying corrupted contextual knowledge. However, important underlying contents are hidden behind the scratches, which are essential hints for producing a semantically consistent result. Motivated by this insight, we explore how to harmonize the scratch-free features and noisy but essential scratch features to produce a visually consistent restoration. Specifically, in this paper, we propose an automatic retouching approach for scratched photographs with the aid of scratch/background context. We explicitly process scratch and background context in two stages. In the first stage, we mainly extract global scratch features, while the mask is introduced in the second stage to filter out and inpaint the scratches. Both contexts are carefully reciprocated for a faithful restoration. Particularly, we propose a Scratch Contextual Assisted Module (SCAM) to adaptively learn texture within the detected mask. This module utilizes the distance between the scratch mask-out feature and scratch encoder feature for modeling the pixel-wise correspondence, which determines the importance of the encoder feature within the scratch mask. Furthermore, to facilitate the evaluation of scratch restoration methods, we create two new scratched photo datasets which have 238 scratch/scratch-free photo pairs to promote the development in the scratch restoration field, namely Old Scratched Photo Dataset (OSPD) and Modern Scratched Photo Dataset (MSPD). Extensive experimental results on the proposed datasets demonstrate that our model outperforms existing methods. To extend the application, we also perform the proposed method on video samples and obtain visual-pleasing results. The code can be found at https://github.com/cwyyt/Contextual-assisted-Scratched-Photo-Restoration 2023-03-13T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/8377 info:doi/10.1109/TCSVT.2023.3256372 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Image restoration Feature extraction Deep learning Electronic mail Context modeling Videos Task analysis Computational Engineering Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Image restoration
Feature extraction
Deep learning
Electronic mail
Context modeling
Videos
Task analysis
Computational Engineering
Graphics and Human Computer Interfaces
spellingShingle Image restoration
Feature extraction
Deep learning
Electronic mail
Context modeling
Videos
Task analysis
Computational Engineering
Graphics and Human Computer Interfaces
CAI, Weiwei
ZHANG, Huaidong
XU, Xuemiao
HE, Shengfeng
ZHANG, Kun
QIN, Jing
Contextual-assisted scratched photo restoration
description Printed photographs can be easily warped, wrinkled, and even deteriorated over time. Existing methods treat the restoration of scratches as a pure inpainting problem that neglects the underlying corrupted contextual knowledge. However, important underlying contents are hidden behind the scratches, which are essential hints for producing a semantically consistent result. Motivated by this insight, we explore how to harmonize the scratch-free features and noisy but essential scratch features to produce a visually consistent restoration. Specifically, in this paper, we propose an automatic retouching approach for scratched photographs with the aid of scratch/background context. We explicitly process scratch and background context in two stages. In the first stage, we mainly extract global scratch features, while the mask is introduced in the second stage to filter out and inpaint the scratches. Both contexts are carefully reciprocated for a faithful restoration. Particularly, we propose a Scratch Contextual Assisted Module (SCAM) to adaptively learn texture within the detected mask. This module utilizes the distance between the scratch mask-out feature and scratch encoder feature for modeling the pixel-wise correspondence, which determines the importance of the encoder feature within the scratch mask. Furthermore, to facilitate the evaluation of scratch restoration methods, we create two new scratched photo datasets which have 238 scratch/scratch-free photo pairs to promote the development in the scratch restoration field, namely Old Scratched Photo Dataset (OSPD) and Modern Scratched Photo Dataset (MSPD). Extensive experimental results on the proposed datasets demonstrate that our model outperforms existing methods. To extend the application, we also perform the proposed method on video samples and obtain visual-pleasing results. The code can be found at https://github.com/cwyyt/Contextual-assisted-Scratched-Photo-Restoration
format text
author CAI, Weiwei
ZHANG, Huaidong
XU, Xuemiao
HE, Shengfeng
ZHANG, Kun
QIN, Jing
author_facet CAI, Weiwei
ZHANG, Huaidong
XU, Xuemiao
HE, Shengfeng
ZHANG, Kun
QIN, Jing
author_sort CAI, Weiwei
title Contextual-assisted scratched photo restoration
title_short Contextual-assisted scratched photo restoration
title_full Contextual-assisted scratched photo restoration
title_fullStr Contextual-assisted scratched photo restoration
title_full_unstemmed Contextual-assisted scratched photo restoration
title_sort contextual-assisted scratched photo restoration
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8377
_version_ 1787136846142111744