编解码器
计算机科学
可变比特率
图像压缩
恒定比特率
数据压缩
编码
图像质量
缩放比例
编码(社会科学)
压缩(物理)
变换编码
图像(数学)
人工智能
计算机工程
图像处理
比特率
数学
电信
统计
基因
复合材料
生物化学
几何学
化学
材料科学
离散余弦变换
出处
期刊:
日期:2020-04-09
卷期号:: 2163-2167
被引量:44
标识
DOI:10.1109/icassp40776.2020.9053885
摘要
Recently, learned image compression has emerged with significant coding efficiency improvement, and even shown noticeable gains over the state-of-the-art traditional codecs. In the mean time, most existing methods need to train separate models for different bitrate target. In this paper, we propose to embed a set of quality scaling factors (SFs) into learned image compression network, by which we can encode images across an entire bitrate range with a single model. This solution offers the comparable performance with those default approaches requiring multiple bitrate dependent models, and reduces the complexity significantly for practical implementation. Our work also demonstrates the generalization for various compression network structures, image contents, and training loss functions.
科研通智能强力驱动
Strongly Powered by AbleSci AI