arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.10184cs.CVcs.LGeess.IV
收藏

使用有损压缩学习更好的无损压缩

Learning Better Lossless Compression Using Lossy Compression

ETH Zurich(苏黎世联邦理工学院);Google Research, Brain Team(谷歌研究院(大脑团队))

Fabian Mentzer, Luc Van Gool, Michael Tschannen

摘要:

我们利用强大的有损图像压缩算法BPG来构建一个无损图像压缩系统。具体地说,原始图像首先分解成后得到的有损重建与BPG压缩和相应的残差。然后,我们用基于卷积神经网络的概率模型对残差的分布进行建模,该概率模型以BPG重建为条件,并将其与熵编码相结合以对残差进行有损压缩编码。最后,使用由BPG和学习的残差编码器产生的比特流的级联来存储图像。由此产生的压缩系统在学习无损全分辨率图像压缩方面实现了最先进的性能,优于以前学习的方法以及PNG,WebP和JPEG 2000。

英文摘要:

We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the corresponding residual. We then model the distribution of the residual with a convolutional neural network-based probabilistic model that is conditioned on the BPG reconstruction, and combine it with entropy coding to losslessly encode the residual. Finally, the image is stored using the concatenation of the bitstreams produced by BPG and the learned residual coder. The resulting compression system achieves state-of-the-art performance in learned lossless full-resolution image compression, outperforming previous learned approaches as well as PNG, WebP, and JPEG2000.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑