Rate-Distortion-Complexity Optimized Framework for Multi-Model Image Compression

doi:10.1109/TIP.2025.3598916

	Rate-Distortion-Complexity Optimized Framework for Multi-Model Image Compression
	Hang, Xinyu 1; Ge, Ziqing 2,3; Fan, Hongfei 4; Jia, Chuanmin 5; Ma, Siwei 6,7; Gao, Wen 6,7
	2025
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	34 页码:5385-5399
摘要	Learned Image Compression (LIC) has experienced rapid growth with the emergence of diverse frameworks. However, the variability in model design and training datasets poses a challenge for the universal application of a single coding model. To address this problem, this paper introduces a pioneering multi-model image coding framework that integrates various image codecs to overcome these limitations. By dynamically allocating codecs to different image regions, our framework optimizes reconstruction quality within the constraints of limited bitrate and decoding time, offering a high-performance, ubiquitous solution for the rate-distortion-complexity trade-off. Our framework features a detailed codec assignment algorithm based on the Simulated Annealing (SA) method, selected for its proven efficacy in managing the discrete and intricate nature of codec assignment optimization. We have implemented a coarse-to-fine strategy, which significantly enhances efficiency. Notably, our framework maintains compatibility with all standard image codecs without necessitating structural modifications. Empirical results indicate that our framework establishes a new standard in LIC, advancing the Pareto frontier for performance-complexity trade-offs. It achieves a significant 70% reduction in decoding time compared to current state-of-the-art methods, without compromising reconstruction quality. Furthermore, under comparable conditions, our approach not only outperforms but significantly eclipses existing Rate-Distortion-Complexity (RDC) optimized codecs, with decoding speeds up to 30 times faster.
关键词	Image coding Codecs Optimization Complexity theory Decoding Distortion Rate-distortion Image reconstruction Bit rate Training Lossy image compression heuristic algorithm rate-distortion-complexity optimization
DOI	10.1109/TIP.2025.3598916
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[62025101] ; Natural Science Foundation of China[62031013] ; Natural Science Foundation of China[62371008] ; Beijing Nova Program ; Ant Group ; New Cornerstone Science Foundation through the XPLORER PRIZE
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001560174700007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41735
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ma, Siwei
作者单位	1.Peking Univ, Sch Comp Sci, State Key Lab Multimedia Informat Proc, Beijing 100871, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 4.Ant Grp, Hangzhou 310000, Peoples R China 5.Peking Univ, Wangxuan Inst Comp Technol, Beijing 100871, Peoples R China 6.Peking Univ, Sch Comp Sci, State Key Lab Multimedia Informat Proc, Beijing 100871, Peoples R China 7.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Hang, Xinyu,Ge, Ziqing,Fan, Hongfei,et al. Rate-Distortion-Complexity Optimized Framework for Multi-Model Image Compression[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2025,34:5385-5399.
APA	Hang, Xinyu,Ge, Ziqing,Fan, Hongfei,Jia, Chuanmin,Ma, Siwei,&Gao, Wen.(2025).Rate-Distortion-Complexity Optimized Framework for Multi-Model Image Compression.IEEE TRANSACTIONS ON IMAGE PROCESSING,34,5385-5399.
MLA	Hang, Xinyu,et al."Rate-Distortion-Complexity Optimized Framework for Multi-Model Image Compression".IEEE TRANSACTIONS ON IMAGE PROCESSING 34(2025):5385-5399.