Improving Image Compression with Adjacent Attention and Refinement Block

Jeny, Afsana Ahsan and Islam, Md Baharul and Junayed, Masum Shah and Das, Debashish (2022) Improving Image Compression with Adjacent Attention and Refinement Block. IEEE Access. ISSN 2169-3536

Preview

Text Improving_Image_Compression_with_Adjacent_Attention_and_Refinem_Aug2022.pdf - Accepted Version Available under License Creative Commons Attribution. Download (18MB)

Abstract

Recently, learned image compression algorithms have shown incredible performance compared to classic hand-crafted image codecs. Despite its considerable achievements, the fundamental disadvantage is not optimized for retaining local redundancies, particularly non-repetitive patterns, which have a detrimental influence on the reconstruction quality. This paper introduces the autoencoder-style network-based efficient image compression method, which contains three novel blocks, i.e., adjacent attention block, Gaussian merge block, and decoded image refinement block, to improve the overall image compression performance. The adjacent attention block allocates the additional bits required to capture spatial correlations (both vertical and horizontal) and effectively remove worthless information. The Gaussian merge block assists the rate-distortion optimization performance, while the decoded image refinement block improves the defects in low-resolution reconstructed images. A comprehensive ablation study analyzes and evaluates the qualitative and quantitative capabilities of the proposed model. Experimental results on two publicly available datasets reveal that our method outperforms the state-of-the-art methods on the KODAK dataset (by around 4dB and 5dB) and CLIC dataset (by about 4dB and 3dB) in terms of PSNR and MS-SSIM.

Item Type:	Article
Identification Number:	10.1109/ACCESS.2022.3195295
Dates:	Date Event 1 August 2022 Accepted 1 August 2022 Published Online
Uncontrolled Keywords:	Image coding, Image reconstruction, Entropy, Transform coding, Entropy coding, Bit rate, Rate-distortion
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science CAH11 - computing > CAH11-01 - computing > CAH11-01-02 - information technology CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence
Divisions:	Faculty of Computing, Engineering and the Built Environment > College of Built Environment
Depositing User:	Debashish Das
Date Deposited:	05 Aug 2022 15:23
Last Modified:	20 Jun 2024 11:45
URI:	https://www.open-access.bcu.ac.uk/id/eprint/13451

Actions (login required)

View Item