End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling

End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling

This article proposes an end-to-end learnt lossy image compression approach, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure with Non-Local Attention optimization and Improved Context modeling (NLAIC). Our NLAIC 1) embeds non-local network operat...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 01., Seite 3179-3191
1. Verfasser: Chen, Tong (VerfasserIn)
Weitere Verfasser: Liu, Haojie, Ma, Zhan, Shen, Qiu, Cao, Xun, Wang, Yao
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM321653718
003 DE-627
005 20231225180334.0
007 cr uuu---uuuuu
008 231225s2021 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2021.3058615  |2 doi 
028 5 2 |a pubmed24n1072.xml 
035 |a (DE-627)NLM321653718 
035 |a (NLM)33606630 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chen, Tong  |e verfasserin  |4 aut 
245 1 0 |a End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling 
264 1 |c 2021 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 26.02.2021 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a This article proposes an end-to-end learnt lossy image compression approach, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure with Non-Local Attention optimization and Improved Context modeling (NLAIC). Our NLAIC 1) embeds non-local network operations as non-linear transforms in both main and hyper coders for deriving respective latent features and hyperpriors by exploiting both local and global correlations, 2) applies attention mechanism to generate implicit masks that are used to weigh the features for adaptive bit allocation, and 3) implements the improved conditional entropy modeling of latent features using joint 3D convolutional neural network (CNN)-based autoregressive contexts and hyperpriors. Towards the practical application, additional enhancements are also introduced to speed up the computational processing (e.g., parallel 3D CNN-based context prediction), decrease the memory consumption (e.g., sparse non-local processing) and reduce the implementation complexity (e.g., a unified model for variable rates without re-training). The proposed model outperforms existing learnt and conventional (e.g., BPG, JPEG2000, JPEG) image compression methods, on both Kodak and Tecnick datasets with the state-of-the-art compression efficiency, for both PSNR and MS-SSIM quality measurements. We have made all materials publicly accessible at https://njuvision.github.io/NIC for reproducible research 
650 4 |a Journal Article 
700 1 |a Liu, Haojie  |e verfasserin  |4 aut 
700 1 |a Ma, Zhan  |e verfasserin  |4 aut 
700 1 |a Shen, Qiu  |e verfasserin  |4 aut 
700 1 |a Cao, Xun  |e verfasserin  |4 aut 
700 1 |a Wang, Yao  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 30(2021) vom: 01., Seite 3179-3191  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:30  |g year:2021  |g day:01  |g pages:3179-3191 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2021.3058615  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 30  |j 2021  |b 01  |h 3179-3191