In recent years, neural image compression (NIC) algorithms have shown powerful coding performance. However, most of them are not adaptive to the image content. Although several contentadaptive methods have been propo...
详细信息
ISBN:
(纸本)9783031197963;9783031197970
In recent years, neural image compression (NIC) algorithms have shown powerful coding performance. However, most of them are not adaptive to the image content. Although several contentadaptive methods have been proposed by updating the encoder-side components, the adaptability of both latents and the decoder is not well exploited. In this work, we propose a new NIC framework that improves the content adaptability on both latents and the decoder. Specifically, to remove redundancy in the latents, our contentadaptive channel dropping (CACD) method automatically selects the optimal quality levels for the latents spatially and drops the redundant channels. Additionally, we propose the contentadaptive feature transformation (CAFT) method to improve decoder-side content adaptability by extracting the characteristic information of the image content, which is then used to transform the features in the decoder side. Experimental results demonstrate that our proposed methods with the encoder-side updating algorithm achieve the state-ofthe-art performance.
暂无评论