Institute of Computing Technology, Chinese Academy IR
Learned Image Compression Using Cross-Component Attention Mechanism | |
Duan, Wenhong1,2; Chang, Zheng3; Jia, Chuanmin4; Wang, Shanshe5; Ma, Siwei5; Song, Li6; Gao, Wen5 | |
2023 | |
发表期刊 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
ISSN | 1057-7149 |
卷号 | 32页码:5478-5493 |
摘要 | Learned image compression methods have achieved satisfactory results in recent years. However, existing methods are typically designed for RGB format, which are not suitable for YUV420 format due to the variance of different formats. In this paper, we propose an information-guided compression framework using cross-component attention mechanism, which can achieve efficient image compression in YUV420 format. Specifically, we design a dual-branch advanced information-preserving module (AIPM) based on the information-guided unit (IGU) and attention mechanism. On the one hand, the dual-branch architecture can prevent changes in original data distribution and avoid information disturbance between different components. The feature attention block (FAB) can preserve the important information. On the other hand, IGU can efficiently utilize the correlations between Y and UV components, which can further preserve the information of UV by the guidance of Y. Furthermore, we design an adaptive cross-channel enhancement module (ACEM) to reconstruct the details by utilizing the relations from different components, which makes use of the reconstructed Y as the textural and structural guidance for UV components. Extensive experiments show that the proposed framework can achieve the state-of-the-art performance in image compression for YUV420 format. More importantly, the proposed framework outperforms Versatile Video Coding (VVC) with 8.37% BD-rate reduction on common test conditions (CTC) sequences on average. In addition, we propose a quantization scheme for context model without model retraining, which can overcome the cross-platform decoding error caused by the floating-point operations in context model and provide a reference approach for the application of neural codec on different platforms. |
关键词 | Image coding Context modeling Transforms Decoding Standards Image reconstruction Transform coding Image compression cross-component information-guided unit attention mechanism information-preserving |
DOI | 10.1109/TIP.2023.3319275 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[62025101] ; National Natural Science Foundation of China[62101007] ; Fundamental Research Funds for the Central Universities ; Young Elite Scientist Sponsorship Program by the Beijing Association for Science and Technology (BAST)[BYSS2022019] ; Wen-Tsun Wu Honorary Doctoral Scholarship ; AI Institute ; Shanghai Jiao Tong University |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:001082264400006 |
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/2XEOYT63/21120 |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Jia, Chuanmin; Ma, Siwei |
作者单位 | 1.Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China 2.Shanghai Jiao Tong Univ, AI Inst, Shanghai 200240, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 4.Peking Univ, Wangxuan Inst Comp Technol WICT, Beijing 100871, Peoples R China 5.Peking Univ, Natl Engn Res Ctr Visual Technol, Sch Comp Sci, Beijing 100871, Peoples R China 6.Shanghai Jiao Tong Univ, Inst Image Commun & Network Engn, AI Inst, Shanghai 200240, Peoples R China |
推荐引用方式 GB/T 7714 | Duan, Wenhong,Chang, Zheng,Jia, Chuanmin,et al. Learned Image Compression Using Cross-Component Attention Mechanism[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:5478-5493. |
APA | Duan, Wenhong.,Chang, Zheng.,Jia, Chuanmin.,Wang, Shanshe.,Ma, Siwei.,...&Gao, Wen.(2023).Learned Image Compression Using Cross-Component Attention Mechanism.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,5478-5493. |
MLA | Duan, Wenhong,et al."Learned Image Compression Using Cross-Component Attention Mechanism".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):5478-5493. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论