Training compression artifacts reduction network with domain adaptation

Yu-Jin Ham; Chaehwa Yoo; Je-Won Kang

doi:10.1117/12.2597094

1 August 2021 Training compression artifacts reduction network with domain adaptation

Yu-Jin Ham, Chaehwa Yoo, Je-Won Kang

Proceedings Volume 11842, Applications of Digital Image Processing XLIV; 118420U (2021) https://doi.org/10.1117/12.2597094
Event: SPIE Optical Engineering + Applications, 2021, San Diego, California, United States

Abstract

Compression artifact removal is imperative for more visually pleasing contents after image and video compression. Recent works on compression artifact reduction network (CARN) assume that the same or similar quality of images would be employed for both training and testing, and, accordingly, a model needs a quality factor as a prior to accomplish the task successfully. However, the possible discrepancy will degrade performance substantially in a target if the model confronts a different level of distortion from the training phase. To solve the problem, we propose a novel training scheme of CARN to take an advantage of domain adaptation (DA). Specifically, we assign an image encoded with a different quality factor as a different domain and train a CARN using DA to perform robustly in another domain of a different level of distortion. Experimental results demonstrate that the proposed method achieves superior performance on DIV2K, BSD68, and Set12.

Conference Presentation

Citation Download Citation

Yu-Jin Ham, Chaehwa Yoo, and Je-Won Kang "Training compression artifacts reduction network with domain adaptation", Proc. SPIE 11842, Applications of Digital Image Processing XLIV, 118420U (1 August 2021); https://doi.org/10.1117/12.2597094

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available