Details
Presenter(s)
![Zongyu Guo Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/21491.jpg?h=30af0297&itok=6APV_KBh)
Display Name
Zongyu Guo
- Affiliation
-
AffiliationUniversity of Science and Technology of China
- Country
Abstract
We have witnessed the revolutionary progress of learned image compression despite a short history of this field. Some challenges still remain such as computational complexity that prevent the practical application of learning-based codecs. In this paper, we address the issue of heavy time complexity from the view of arithmetic coding. We make use of channel-adaptive codebooks that cover more appropriate ranges to reduce the runtime of compression. Experimental results demonstrate that both the arithmetic encoding and decoding can be accelerated while preserving the rate-distortion performance of learned compression model.