Asymmetric Learned Image Compression With Multi-Scale Residual Block, Importance Scaling, and Post-Quantization Filtering-Reference-Cited by-同舟云学术

Asymmetric Learned Image Compression With Multi-Scale Residual Block, Importance Scaling, and Post-Quantization Filtering

Author:

Fu Haisheng¹^ORCID,Liang Feng¹^ORCID,Liang Jie²^ORCID,Li Binglin²^ORCID,Zhang Guohe¹^ORCID,Han Jingning³^ORCID

Affiliation:

1. School of Microelectronics, Xi’an Jiaotong University, Xi’an, China

2. School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada

3. Google Inc., Mountain View, CA, USA

Funder

National Natural Science Foundation of China

Natural Science Foundation of Shaanxi Province, China

Natural Sciences and Engineering Research Council of Canada

China Scholarship Council

Google Chrome University Research Program

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Media Technology

Link

Reference48 articles.

3. Soft-to-hard vector quantization for end-to-end learning compressible representations;agustsson;Proc Adv Neural Inf Process Syst,2017

5. Variational autoencoder for low bit-rate image compression;zhou;Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) Workshops,2018

Cited by 10 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

4. Efficient Learned Image Compression with Selective Kernel Residual Module and Channel-Wise Causal Context Model;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14