Skip to main navigation Skip to search Skip to main content

Entropy Relaxed Lattice Vector Quantization for Learned Image Compression

  • Maida Cao*
  • , Wenrui Dai
  • , Shaohui Li
  • , Han Li
  • , Chenglin Li
  • , Junni Zou
  • , Hongkai Xiong
  • *Corresponding author for this work
  • Shanghai Jiao Tong University
  • Tsinghua University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Learned image compression (LIC) has recently emerged as a promising alternative to realize transform-based coding. Contrary to widely studied transform and entropy modeling in LIC, most LIC methods are limited to uniform scalar quantization and existing vector quantization (VQ) methods are restricted by the soft-to-hard quantization strategy. In this paper, we propose a novel entropy relaxed lattice vector quantization (ERLVQ) scheme for LIC. ERLVQ achieves a tractable dimension-wise approximation to the probability mass function for the complex Voronoi regions in a general class of lattices. Instead of directly performing probabilistic estimation on the lattices, ERLVQ equivalently aligns complex Voronoi regions with a set of complete and non-overlapping hypercubes in a projected parametric domain. Space covering technique is then developed to generating hypercubes with their centers fixed to integer projected lattice points and their volumes equaling the Voronoi regions to enable separable dimension-wise estimation of multi-variate probability mass functions. The proposed ERLVQ is the first to adapt to arbitrary lattices for VQ based on LIC and can be embedded into existing LIC methods. Experimental results demonstrate that the proposed ERLVQ is superior to the uniform scalar quantization (USQ) and existing lattice VQ methods [1] on prevailing LIC baselines, as shown in Table 1.

Original languageEnglish
Title of host publicationProceedings - DCC 2024
Subtitle of host publication2024 Data Compression Conference
EditorsAli Bilgin, James E. Fowler, Joan Serra-Sagrista, Yan Ye, James A. Storer
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages548
Number of pages1
ISBN (Electronic)9798350385878
DOIs
StatePublished - 2024
Externally publishedYes
Event2024 Data Compression Conference, DCC 2024 - Snowbird, United States
Duration: 19 Mar 2024 → 22 Mar 2024

Publication series

NameData Compression Conference Proceedings
ISSN (Print)1068-0314

Conference

Conference2024 Data Compression Conference, DCC 2024
Country/TerritoryUnited States
CitySnowbird
Period19/03/24 → 22/03/24

Fingerprint

Dive into the research topics of 'Entropy Relaxed Lattice Vector Quantization for Learned Image Compression'. Together they form a unique fingerprint.

Cite this