LUT-LIC: Look-Up Table-Assisted Learned Image Compression

Seung Eun Yu, Jong Seok Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Image compression is indispensable in many visual applications. Recently, learned image compression (LIC) using deep learning has surpassed traditional image codecs such as JPEG in terms of compression efficiency but at the cost of increased complexity. Thus, employing LIC in resource-limited environments is challenging. In this paper, we propose an LIC model using a look-up table (LUT) to effectively reduce the complexity. Specifically, we design an LUT replacing the entropy decoder by analyzing its input characteristics and accordingly developing a dynamic sampling method for determining the indices of the LUT. Experimental results show that the proposed method achieves better compression efficiency than traditional codecs with faster runtime than existing LIC models.

Original languageEnglish
Title of host publicationNeural Information Processing - 30th International Conference, ICONIP 2023, Proceedings
EditorsBiao Luo, Long Cheng, Zheng-Guang Wu, Hongyi Li, Chaojie Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages430-441
Number of pages12
ISBN (Print)9789819981472
DOIs
Publication statusPublished - 2024
Event30th International Conference on Neural Information Processing, ICONIP 2023 - Changsha, China
Duration: 2023 Nov 202023 Nov 23

Publication series

NameCommunications in Computer and Information Science
Volume1966 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference30th International Conference on Neural Information Processing, ICONIP 2023
Country/TerritoryChina
CityChangsha
Period23/11/2023/11/23

Bibliographical note

Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'LUT-LIC: Look-Up Table-Assisted Learned Image Compression'. Together they form a unique fingerprint.

Cite this