APSIPA Transactions on Signal and Information Processing > Vol 14 > Issue 1

Generative Coding: Promise and Challenges

Siwei Ma, Peking University, China, swma@pku.edu.cn , Shenpeng Song, Peking University, China, Bolin Chen, City University of Hong Kong, China, Qi Mao, Communication University of China, China, Xiaohan Fang, City University of Hong Kong, China, Chuanmin Jia, Peking University, China, Shiqi Wang, City University of Hong Kong, China
 
Suggested Citation
Siwei Ma, Shenpeng Song, Bolin Chen, Qi Mao, Xiaohan Fang, Chuanmin Jia and Shiqi Wang (2025), "Generative Coding: Promise and Challenges", APSIPA Transactions on Signal and Information Processing: Vol. 14: No. 1, e33. http://dx.doi.org/10.1561/116.20250056

Publication Date: 19 Nov 2025
© 2025 S. Ma, S. Song, B. Chen, Q. Mao, X. Fang, C. Jia and S. Wang
 
Subjects
Data compression,  Rate-distortion theory,  Source coding,  Coding theory and practice,  Signal processing for communications,  Image and video processing,  Coding and compression,  Subband and transform methods,  Statistical/Machine learning,  Learning and statistical methods
 
Keywords
Image and video compressiongenerative compression
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 7 times

In this article:
Introduction 
Generative Coding: Formulation and Paradigm 
Generative Coding: Progress Survey 
Generative Coding: Key Issues 
Experiment 
Conclusion 
References 

Abstract

Traditional image and video compression techniques, based on handcrafted transforms and distortion metrics, have proven effective in earlier applications. However, their inherent limitations in coding efficiency and perceptual quality become increasingly evident when faced with the demands of diverse and semantically complex visual content. With advances in deep generative models, generative coding has emerged as a promising alternative, offering improved efficiency, perceptual quality, and flexibility. However, it also poses challenges in complexity, interpretability, and deployment. This survey provides a comprehensive overview of generative coding. We formalize the problem and highlight its theoretical links to generation and compression. Representative methods are categorized by model type and technical evolution. Finally, we further present comparative experiments and discuss key challenges and future directions to guide ongoing research.

DOI:10.1561/116.20250056