Spatial Competition for Low-Complexity Learned Image Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Blard, Théophile, Philippe, Pierrick, Ladune, Théo, Jiang, Xiaoran, Déforges, Olivier
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916008889942016
author Blard, Théophile
Philippe, Pierrick
Ladune, Théo
Jiang, Xiaoran
Déforges, Olivier
author_facet Blard, Théophile
Philippe, Pierrick
Ladune, Théo
Jiang, Xiaoran
Déforges, Olivier
contents Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a low-complexity learned image compression framework based on spatial competition between multiple specialized neural codecs. For each image region, the encoder selects the codec that best matches the local content according to a rate-distortion cost. A mode map is transmitted as side information to indicate the per-region codec selection. At decoding time, this mode map-based selection guides reconstruction while preserving the complexity of a single codec. This design enables per-image adaptation with low decoding complexity and fast encoding. On the CLIC 2020 dataset, our method achieves up to -14.5% rate reduction compared to a single codec and reaches HEVC-level performance with a decoding complexity of 1433 MACs per pixel.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13243
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spatial Competition for Low-Complexity Learned Image Compression
Blard, Théophile
Philippe, Pierrick
Ladune, Théo
Jiang, Xiaoran
Déforges, Olivier
Image and Video Processing
Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a low-complexity learned image compression framework based on spatial competition between multiple specialized neural codecs. For each image region, the encoder selects the codec that best matches the local content according to a rate-distortion cost. A mode map is transmitted as side information to indicate the per-region codec selection. At decoding time, this mode map-based selection guides reconstruction while preserving the complexity of a single codec. This design enables per-image adaptation with low decoding complexity and fast encoding. On the CLIC 2020 dataset, our method achieves up to -14.5% rate reduction compared to a single codec and reaches HEVC-level performance with a decoding complexity of 1433 MACs per pixel.
title Spatial Competition for Low-Complexity Learned Image Compression
topic Image and Video Processing
url https://arxiv.org/abs/2605.13243