论文标题
深度学习改进的图像编码自动编码器
Improved Image Coding Autoencoder With Deep Learning
论文作者
论文摘要
在本文中，我们基于Ballé的方法构建了基于自动编码器的管道，以实现极端端到端的图像压缩，这是使用深度学习的图像压缩中最新的开源开源实现。我们通过在每个跨越的卷积层上使用相同数量的下采样和向上采样的卷积层加深一个隐藏层加深了网络。我们的方法表现优于Ballé的方法，并且每个像素（BPP）的位降低了约4.0％，多尺度结构相似性（MS-SSIM）增加了0.03％，仅峰值信噪比（PSNR）降低了0.47％，它也均超过了所有传统图像压缩方法，包括所有传统图像压缩效率，至少均超过了Jepegs and Imagers Atsimition，至少是JEPED效率，至少是ATEAR IMAGIONT AT AT AT AT AT AT AT AT AT ATEARICITION，ATER效率是ATAT AT AT AT AT ATECICERTION，ATICERITION AT ATECINITION AT AT ATECICERTION，ATICER效率 质量。关于编码和解码时间，与GPU的支持相比，我们的方法需要类似的时间，这意味着它几乎可以适应工业应用。
In this paper, we build autoencoder based pipelines for extreme end-to-end image compression based on Ballé's approach, which is the state-of-the-art open source implementation in image compression using deep learning. We deepened the network by adding one more hidden layer before each strided convolutional layer with exactly the same number of down-samplings and up-samplings. Our approach outperformed Ballé's approach, and achieved around 4.0% reduction in bits per pixel (bpp), 0.03% increase in multi-scale structural similarity (MS-SSIM), and only 0.47% decrease in peak signal-to-noise ratio (PSNR), It also outperforms all traditional image compression methods including JPEG2000 and HEIC by at least 20% in terms of compression efficiency at similar reconstruction image quality. Regarding encoding and decoding time, our approach takes similar amount of time compared with traditional methods with the support of GPU, which means it's almost ready for industrial applications.
