Efficient Learned Image Compression with Selective Kernel Residual Module and Channel-Wise Causal Context Model

Recently, learning-based image compression approaches have achieved superior performance over classical image compression methods. However, their complexities remain quite high. In this paper, we propose two efficient modules to reduce the complexity. First, we introduce a selective kernel residual...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) S. 4040 - 4044
Hauptverfasser: Fu, Haisheng, Liang, Feng, Liang, Jie, Fang, Zhenman, Zhang, Guohe, Han, Jingning
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 14.04.2024
Schlagworte:
Channel-wise causal context model
Complexity theory
Decoding
Image coding
Learning systems
Learning-based image compression
Measurement
Rate-distortion
Selective kernel residual module
Signal processing
ISSN:2379-190X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recently, learning-based image compression approaches have achieved superior performance over classical image compression methods. However, their complexities remain quite high. In this paper, we propose two efficient modules to reduce the complexity. First, we introduce a selective kernel residual module into the core network, which effectively expands the receptive field and captures global information. Second, we present an improved channel-wise causal context model, designed to not only reduce encoding and decoding time but also ensure rate-distortion performance. Experimental results demonstrate that our proposed method achieves better tradeoff than recent leading learned image compression methods, and also outperforms the latest H.266/VVC (4:4:4) in terms of PSNR and MS-SSIM metrics.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10447420