论文标题
3-D上下文熵模型，用于改进实际图像压缩
3-D Context Entropy Model for Improved Practical Image Compression
论文作者
论文摘要
在本文中，我们介绍了为CLIC 2020竞赛设计的图像压缩框架。我们的方法基于变异自动编码器（VAE）结构，该体系结构通过残留结构增强。简而言之，我们在这里进行了三个值得注意的改进。首先，我们提出了一个3-D上下文熵模型，该模型可以利用当前空间位置中的已知潜在表示，以更好地熵估计。其次，在熵估计过程中采用了轻加权的残余结构来进行特征学习。最后，引入了一种有效的培训策略，以通过不同的分辨率进行实践适应。实验结果表明，我们的图像压缩方法在CLIC验证集上达到了0.9775 ms-SSIM，在测试集上达到了0.9809 ms-SSIM。
In this paper, we present our image compression framework designed for CLIC 2020 competition. Our method is based on Variational AutoEncoder (VAE) architecture which is strengthened with residual structures. In short, we make three noteworthy improvements here. First, we propose a 3-D context entropy model which can take advantage of known latent representation in current spatial locations for better entropy estimation. Second, a light-weighted residual structure is adopted for feature learning during entropy estimation. Finally, an effective training strategy is introduced for practical adaptation with different resolutions. Experiment results indicate our image compression method achieves 0.9775 MS-SSIM on CLIC validation set and 0.9809 MS-SSIM on test set.
