Learned Image Compression With Efficient Cross-Platform Entropy Coding

Learned image compression has shown remarkable compression efficiency gain over the traditional image compression solutions, which is partially attributed to the learned entropy models and the adopted entropy coding engine. However, the inference of the entropy models and the sequential nature of th...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE journal on emerging and selected topics in circuits and systems Ročník 15; číslo 1; s. 72 - 82
Hlavní autori: Yang, Runyu, Liu, Dong, Wu, Feng, Gao, Wen
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.03.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Block-based coding
chain coding
Circuits and systems
Coding
Complexity
Computational modeling
cross-platform consistency
Decoding
Entropy
Entropy coding
Estimation
Floating point arithmetic
Image coding
Image compression
learned image compression
Neural networks
Symbols
Time complexity
Training
Transforms
ISSN:2156-3357, 2156-3365
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Learned image compression has shown remarkable compression efficiency gain over the traditional image compression solutions, which is partially attributed to the learned entropy models and the adopted entropy coding engine. However, the inference of the entropy models and the sequential nature of the entropy coding both incur high time complexity. Meanwhile, the neural network-based entropy models usually involve floating-point computations, which incur inconsistent probability estimation and decoding failure in different platforms. We address these limitations by introducing an efficient and cross-platform entropy coding method, chain coding-based latent compression (CC-LC), into learned image compression. First, we leverage the classic chain coding and carefully design a block-based entropy coding procedure, significantly reducing the number of coding symbols and thus the coding time. Second, since CC-LC is not based on neural networks, we propose a rate estimation network as a surrogate of CC-LC during the end-to-end training. Third, we alternately train the analysis/synthesis networks and the rate estimation network for the rate-distortion optimization, making the learned latent fit CC-LC. Experimental results show that our method achieves much lower time complexity than the other learned image compression methods, ensures cross-platform consistency, and has comparable compression efficiency with BPG. Our code and models are publicly available at https://github.com/Yang-Runyu/CC-LC .
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2156-3357
2156-3365
DOI:10.1109/JETCAS.2025.3538652