论文标题
$ \ ell_ \ infty $限制的编码和深度解码
Ultra High Fidelity Image Compression with $\ell_\infty$-constrained Encoding and Deep Decoding
论文作者
论文摘要
在许多专业领域，例如医学，遥感和科学领域，用户经常要求图像压缩方法在数学上是无损的。但是无损图像编码的压缩比（自然图像约为2：1）。在满足严格的保真度要求的同时，唯一已知的实现重大压缩的技术是$ \ ell_ \ infty $受约束的编码的方法，该方法是在90年代开发和标准化的。在$ \ ell_ \ infty $约束的图像编码二十年后，我们通过开发一种基于CNN的新型软$ \ ell_ \ infty $约束的解码方法来取得重大进展。新方法通过使用称为$ \ ell_ \ infty \ mbox { - sdnet} $的恢复CNN来修复压缩缺陷，以将常规解码的图像映射到潜在图像。 $ \ ell_ \ infty \ mbox {-sdnet} $的独特强度是其在按像素基础上绑定的紧密错误的能力。因此，即使是由主流CNN恢复方法牺牲的统计异常值，也可以删除或扭曲原始图像的独特结构。更重要的是，这项研究将$ \ ell_ \ infty $限制的编码和深软解码的新图像压缩系统（$ \ ell_ \ elfty \ mbox {-ed}^2 $）。 $ \ ell_ \ infty \ mbox {-ed}^2 $方法击败了现有有损的图像压缩方法（例如，bpg，webp等），不仅在$ \ ell_ \ infty $中，而且还以$ \ ell_ \ infty $，而且还以$ \ ell_2 $错误的质量和感知的质量，对于比特的质量，比特率接近近距离的近距离近距离替代差异。在操作上，新的压缩系统是实用的，具有低复杂的实时编码器和由快速初始解码器和可选的CNN软解码器组成的级联解码器。
In many professional fields, such as medicine, remote sensing and sciences, users often demand image compression methods to be mathematically lossless. But lossless image coding has a rather low compression ratio (around 2:1 for natural images). The only known technique to achieve significant compression while meeting the stringent fidelity requirements is the methodology of $\ell_\infty$-constrained coding that was developed and standardized in nineties. We make a major progress in $\ell_\infty$-constrained image coding after two decades, by developing a novel CNN-based soft $\ell_\infty$-constrained decoding method. The new method repairs compression defects by using a restoration CNN called the $\ell_\infty\mbox{-SDNet}$ to map a conventionally decoded image to the latent image. A unique strength of the $\ell_\infty\mbox{-SDNet}$ is its ability to enforce a tight error bound on a per pixel basis. As such, no small distinctive structures of the original image can be dropped or distorted, even if they are statistical outliers that are otherwise sacrificed by mainstream CNN restoration methods. More importantly, this research ushers in a new image compression system of $\ell_\infty$-constrained encoding and deep soft decoding ($\ell_\infty\mbox{-ED}^2$). The $\ell_\infty \mbox{-ED}^2$ approach beats the best of existing lossy image compression methods (e.g., BPG, WebP, etc.) not only in $\ell_\infty$ but also in $\ell_2$ error metric and perceptual quality, for bit rates near the threshold of perceptually transparent reconstruction. Operationally, the new compression system is practical, with a low-complexity real-time encoder and a cascade decoder consisting of a fast initial decoder and an optional CNN soft decoder.
