LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transforms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ameen, Ayman A., Richter, Thomas, Kaup, André
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908344059428864
author Ameen, Ayman A.
Richter, Thomas
Kaup, André
author_facet Ameen, Ayman A.
Richter, Thomas
Kaup, André
contents Current learned image compression models typically exhibit high complexity, which demands significant computational resources. To overcome these challenges, we propose an innovative approach that employs hierarchical feature extraction transforms to significantly reduce complexity while preserving bit rate reduction efficiency. Our novel architecture achieves this by using fewer channels for high spatial resolution inputs/feature maps. On the other hand, feature maps with a large number of channels have reduced spatial dimensions, thereby cutting down on computational load without sacrificing performance. This strategy effectively reduces the forward pass complexity from \(1256 \, \text{kMAC/Pixel}\) to just \(270 \, \text{kMAC/Pixel}\). As a result, the reduced complexity model can open the way for learned image compression models to operate efficiently across various devices and pave the way for the development of new architectures in image compression technology.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21778
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transforms
Ameen, Ayman A.
Richter, Thomas
Kaup, André
Image and Video Processing
Computer Vision and Pattern Recognition
Current learned image compression models typically exhibit high complexity, which demands significant computational resources. To overcome these challenges, we propose an innovative approach that employs hierarchical feature extraction transforms to significantly reduce complexity while preserving bit rate reduction efficiency. Our novel architecture achieves this by using fewer channels for high spatial resolution inputs/feature maps. On the other hand, feature maps with a large number of channels have reduced spatial dimensions, thereby cutting down on computational load without sacrificing performance. This strategy effectively reduces the forward pass complexity from \(1256 \, \text{kMAC/Pixel}\) to just \(270 \, \text{kMAC/Pixel}\). As a result, the reduced complexity model can open the way for learned image compression models to operate efficiently across various devices and pave the way for the development of new architectures in image compression technology.
title LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transforms
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.21778