Salvato in:
Dettagli Bibliografici
Autori principali: Liang, Zijian, Niu, Kai, Wang, Changshuo, Xu, Jin, Zhang, Ping
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.22438
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910972835266560
author Liang, Zijian
Niu, Kai
Wang, Changshuo
Xu, Jin
Zhang, Ping
author_facet Liang, Zijian
Niu, Kai
Wang, Changshuo
Xu, Jin
Zhang, Ping
contents Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this paper, we propose a synonymous variational inference (SVI) method based on this synonymity viewpoint to re-analyze the perceptual image compression problem. It takes perceptual similarity as a typical synonymous criterion to build an ideal synonymous set (Synset), and approximate the posterior of its latent synonymous representation with a parametric density by minimizing a partial semantic KL divergence. This analysis theoretically proves that the optimization direction of perception image compression follows a triple tradeoff that can cover the existing rate-distortion-perception schemes. Additionally, we introduce synonymous image compression (SIC), a new image compression scheme that corresponds to the analytical process of SVI, and implement a progressive SIC codec to fully leverage the model's capabilities. Experimental results demonstrate comparable rate-distortion-perception performance using a single progressive SIC codec, thus verifying the effectiveness of our proposed analysis method.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22438
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Synonymous Variational Inference for Perceptual Image Compression
Liang, Zijian
Niu, Kai
Wang, Changshuo
Xu, Jin
Zhang, Ping
Information Theory
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this paper, we propose a synonymous variational inference (SVI) method based on this synonymity viewpoint to re-analyze the perceptual image compression problem. It takes perceptual similarity as a typical synonymous criterion to build an ideal synonymous set (Synset), and approximate the posterior of its latent synonymous representation with a parametric density by minimizing a partial semantic KL divergence. This analysis theoretically proves that the optimization direction of perception image compression follows a triple tradeoff that can cover the existing rate-distortion-perception schemes. Additionally, we introduce synonymous image compression (SIC), a new image compression scheme that corresponds to the analytical process of SVI, and implement a progressive SIC codec to fully leverage the model's capabilities. Experimental results demonstrate comparable rate-distortion-perception performance using a single progressive SIC codec, thus verifying the effectiveness of our proposed analysis method.
title Synonymous Variational Inference for Perceptual Image Compression
topic Information Theory
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2505.22438