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

Haisheng Fu; Feng Liang; Jie Liang; Zhenman Fang; Guohe Zhang; Jingning Han

ICASSP 2024accepted0 citations

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

Haisheng Fu, Feng Liang, Jie Liang, Zhenman Fang, Guohe Zhang, Jingning Han

Abstract

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.

BibTeX

@inproceedings{icassp2024_efficientlearned,
  title = {Efficient Learned Image Compression with Selective Kernel Residual Module and Channel-Wise Causal Context Model},
  author = {Haisheng Fu and Feng Liang and Jie Liang and Zhenman Fang and Guohe Zhang and Jingning Han},
  booktitle = {ICASSP 2024},
  year = {2024}
}