Universal Efficient Variable-Rate Neural Image Compression

Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate flexibility are still two major challenges for its practical deployment. To tackle these problems, this paper proposes two...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 2025 - 2029
Main Authors Yin, Shanzhi, Li, Chao, Bao, Youneng, Liang, Yongsheng, Meng, Fanyang, Liu, Wei
Format Conference Proceeding
LanguageEnglish
Published IEEE 23.05.2022
Subjects
Adaptation models
Computational modeling
Convolution
dynamic pruning
Image coding
image compression
Modulation
Training
Transform coding
variable-rate
Online AccessGet full text
ISSN2379-190X
DOI10.1109/ICASSP43922.2022.9747854

Cover

More Information
Summary:Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate flexibility are still two major challenges for its practical deployment. To tackle these problems, this paper proposes two universal modules named Energy-based Channel Gating(ECG) and Bit-rate Modulator(BM), which can be directly embedded into existing end-to-end image compression models. ECG uses dynamic pruning to reduce FLOPs for more than 50% in convolution layers, and a BM pair can modulate the latent representation to control the bit-rate in a channel-wise manner. By implementing these two modules, existing learning-based image codecs can obtain ability to output arbitrary bit-rate with a single model and reduced computation.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747854