Multi-hypothesis inspired super-resolution for compression distorted screen content image

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationApplications of Digital Image Processing XLIV
EditorsAndrew G. Tescher, Touradj Ebrahimi
PublisherSPIE
ISBN (Electronic)9781510645233
ISBN (Print)9781510645226
Publication statusPublished - 2021

Publication series

NameProceedings of SPIE
Volume11842
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

TitleSPIE Optics + Photonics 2021 (ODS 2021)
PlaceUnited States
CitySan Diego
Period1 - 5 August 2021

Abstract

Multi-hypothesis-based prediction has been repetitively proven to be effective in improving prediction accuracy and enhancing coding performance. In this paper, we introduce the principle of multi-hypothesis to the super-resolution (SR) of compressed screen content images, with the goal of improving the restoration quality of the compression contaminated screen content images. More specifically, the super-resolution is achieved by a deep neural network. The deep neural network learns the mapping relationship between the compressed low-resolution (LR) image and the original high-resolution (HR) image. During learning process, we feed multiple LR patches for training, including the current patch and five neighboring patches, providing more informative clues for the learning of the high-quality restoration. In the inference process, input LR image will be translated with random offsets, yielding five assistant LR items for the SR of the input LR image. The LR and assistant LR items employ separate modules for feature extraction and then the features are fused with concatenation. Subsequently, the deep residual feature extraction is applied, which is composed of multiple consecutive residual blocks. Finally, the deep features are reconstructed with pixel shuffle, producing the SR image. Experimental results verify the effectiveness of the proposed multi-hypothesis-based SR scheme.

Research Area(s)

  • Multihypothesis, Screen content, Super resolution, VVC

Citation Format(s)

Multi-hypothesis inspired super-resolution for compression distorted screen content image. / Wang, Meng; Xu, Jizheng; Zhang, Li et al.

Applications of Digital Image Processing XLIV. ed. / Andrew G. Tescher; Touradj Ebrahimi. SPIE, 2021. 1184206 (Proceedings of SPIE; Vol. 11842).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review